INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    65
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    terms related to compliance and authority within regulated contexts

    New Auto-Interp
    Negative Logits
     Wikimedijinoj
    -0.52
     Audiodateien
    -0.49
    -0.47
    Personensuche
    -0.46
    MessageOf
    -0.46
    WriteTagHelper
    -0.46
    󠁣
    -0.46
     Picchu
    -0.45
    Kariera
    -0.44
    etsa
    -0.44
    POSITIVE LOGITS
     betweenstory
    0.47
     conditions
    0.45
     limitaciones
    0.44
     limitation
    0.42
     limited
    0.41
    LookAnd
    0.41
    ActivityCompat
    0.41
    制限
    0.40
     restricted
    0.40
     condiciones
    0.40
    Act Density 0.000%

    No Known Activations