INDEX
Model
gemma-2-9b-it
Layer #
20
Steering Hook
blocks.20.hook_resid_pre
Steering Strength
85.5
Uploader
bot-neuronpedia
Created At
2/15/2025 1:06:43 AM
Raw Vector
Actions
Explanations
concepts related to relationships and connections between individuals or communities
New Auto-Interp
Negative Logits
TextAppearance
-0.51
Elector
-0.46
"}")
-0.45
Appellee
-0.44
doria
-0.44
magister
-0.43
sistors
-0.43
Dominant
-0.43
Conventional
-0.42
)»
-0.42
POSITIVE LOGITS
connection
0.67
connections
0.66
relationship
0.65
relationships
0.64
bond
0.61
conexión
0.59
connect
0.59
connection
0.58
connections
0.58
hubungan
0.57
Activations Density 0.012%