INDEX
Model
gemma-2-9b-it
Layer #
20
Steering Hook
blocks.20.hook_resid_pre
Steering Strength
68.5
Uploader
bot-neuronpedia
Created At
2/15/2025 1:06:43 AM
Raw Vector
Actions
Explanations
terms related to documentation and compliance
New Auto-Interp
Negative Logits
zheimer
-0.48
styleType
-0.48
tanleria
-0.45
annica
-0.44
esternos
-0.44
Smarty
-0.44
AssemblyCulture
-0.42
Lokales
-0.42
sistors
-0.42
HttpFoundation
-0.42
POSITIVE LOGITS
FormState
0.52
evidence
0.51
ValueStyle
0.49
compliance
0.49
Compliance
0.48
documentation
0.45
Evidence
0.44
Compliance
0.44
validation
0.43
evidence
0.43
Activations Density 0.000%