A real Gemma 2 (2B) has a dial for each concept it knows. Drag one and the model
leans toward it — or away from it — until you let go and it’s exactly, provably itself again,
because nothing was ever written to a weight. Every dial below does that same thing to the
model. What changes is only how the dial's direction was found.
SAE feature— a sparse autoencoder already learned this direction from the model's own activations, one of ~16,000 candidates.
ActAdd contrast pair— no autoencoder: the direction is just the difference between two prompts, written by hand.
loading…
The ActAdd bank is showing sample data — hand-authored, illustrative placeholders, not model
output. Regenerate with build_actadd.py.