INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    52.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    punctuation marks and other formatting indicators

    New Auto-Interp
    Negative Logits
     nawr
    -0.37
     switch
    -0.35
    ณ์
    -0.32
    -0.31
     철
    -0.31
    )
    -0.31
    :@"
    -0.30
    (&:
    -0.30
     vapour
    -0.29
     wield
    -0.29
    POSITIVE LOGITS
     kasarigan
    0.82
    ſelf
    0.73
     purpoſe
    0.69
     AssemblyCompany
    0.68
    ſelves
    0.66
    rrggbb
    0.64
     betweenstory
    0.64
     queſta
    0.64
    AsUp
    0.63
     Infórmanos
    0.63
    Act Density 0.839%

    No Known Activations