INDEX
Model
gemma-2-9b-it
Layer #
20
Steering Hook
blocks.20.hook_resid_pre
Steering Strength
42.75
Uploader
bot-neuronpedia
Created At
2/15/2025 1:06:43 AM
Raw Vector
Actions
Explanations
key terms and phrases related to technical specifications and legal concepts
New Auto-Interp
Negative Logits
indépendance
-0.30
īpa
-0.28
-0.28
legais
-0.27
kullanım
-0.27
beliau
-0.27
extrémité
-0.27
réservoir
-0.27
interprétation
-0.27
veramente
-0.26
POSITIVE LOGITS
<unused1>
0.81
<unused14>
0.81
<unused41>
0.81
[@BOS@]
0.81
<unused3>
0.81
<unused21>
0.81
<unused28>
0.81
<unused51>
0.81
<unused68>
0.81
<unused74>
0.81
Activations Density 4.189%