INDEX
Model
gemma-2-9b-it
Layer #
20
Steering Hook
blocks.20.hook_resid_pre
Steering Strength
59.75
Uploader
bot-neuronpedia
Created At
2/15/2025 1:06:43 AM
Raw Vector
Actions
Explanations
words related to social connections and group dynamics
New Auto-Interp
Negative Logits
Personendaten
-0.73
GEBURTSDATUM
-0.59
</thead>
-0.55
estacks
-0.55
LabelTagHelper
-0.54
GEBURTS
-0.54
httphttps
-0.53
jsxFileName
-0.52
Paglinawan
-0.52
المناصب
-0.51
POSITIVE LOGITS
blessés
0.42
morale
0.40
injuries
0.39
Störungen
0.38
ไหม
0.36
ValueStyle
0.36
blessures
0.35
relationships
0.34
blessé
0.34
emotionally
0.33
Activations Density 0.000%