INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    43.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    specific identifiers or names in code and documentation contexts

    New Auto-Interp
    Negative Logits
     незавершена
    -0.66
    Personendaten
    -0.63
     Paglinawan
    -0.61
    GEBURTS
    -0.57
     ویکی‌پدی
    -0.55
     nonUne
    -0.54
    ]]:
    -0.52
     Italijanski
    -0.50
    -0.50
     kaarangay
    -0.50
    POSITIVE LOGITS
    erende
    0.48
     propOrder
    0.43
     chaud
    0.42
    Története
    0.41
     solitario
    0.39
     révélé
    0.39
    конча
    0.38
     révèle
    0.38
     financiero
    0.38
    ők
    0.37
    Act Density 0.007%

    No Known Activations