INDEX
Model
gemma-2-9b-it
Layer #
20
Steering Hook
blocks.20.hook_resid_pre
Steering Strength
38.5
Uploader
bot-neuronpedia
Created At
2/15/2025 1:06:43 AM
Raw Vector
Actions
Explanations
instances of legal and regulatory language
New Auto-Interp
Negative Logits
miteinander
-0.42
pungkas
-0.38
}{*}{-0.38
brigens
-0.37
attente
-0.35
Vereinig
-0.35
sobie
-0.35
modifikasi
-0.34
penumpang
-0.34

-0.33
POSITIVE LOGITS
rrggbb
0.73
transQ
0.59
bibfield
0.59
تضيفلها
0.57
propOrder
0.57
addCriterion
0.54
0.53
setVerticalGroup
0.52
TemporalType
0.52
Билгалдахарш
0.50
Activations Density 5.988%