Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    51.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    tokens that signify the end of a sentence or significant pauses in text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Audiodateien
    -0.45
     esternos
    -0.43
     compress
    -0.41
     Hipp
    -0.41
    onghi
    -0.39
    pops
    -0.37
    󠁣
    -0.37
    íncia
    -0.36
    Incorrect
    -0.35
    engeance
    -0.35
    POSITIVE LOGITS
    LookAnd
    0.66
    AutoScaleMode
    0.57
     autorytatywna
    0.52
     purpoſe
    0.50
    fromnode
    0.50
    PerformLayout
    0.50
    Manbalar
    0.49
    帖最后由
    0.49
    InstrumentedTest
    0.47
    DisplayMetrics
    0.46
    Act Density 0.360%

    No Known Activations