INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    72.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    terms related to conflicts of interest

    New Auto-Interp
    Negative Logits
    OGND
    -0.79
    GEBURTSDATUM
    -0.64
    :✨
    -0.63
    bootstrapcdn
    -0.62
     Larg
    -0.57
    httphttps
    -0.57
    Personendaten
    -0.57
    zheimer
    -0.57
    出版年
    -0.56
     ProtoMessage
    -0.55
    POSITIVE LOGITS
    Manbalar
    0.40
     dévo
    0.39
    sihkan
    0.37
    quele
    0.36
    Align
    0.35
    Chham
    0.35
     affaires
    0.34
     estrategias
    0.34
     når
    0.32
     circunstancias
    0.32
    Act Density 0.002%

    No Known Activations