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
    57.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    punctuation and sentence-ending marks

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     elettrica
    -0.33
    Smarty
    -0.32
    énéral
    -0.32
     famously
    -0.32
    ToMany
    -0.31
     Feier
    -0.31
     histórica
    -0.31
     unplug
    -0.30
    newArrayList
    -0.30
    énergie
    -0.30
    POSITIVE LOGITS
     betweenstory
    0.71
     purpoſe
    0.69
    ſelf
    0.65
    ſelves
    0.65
     ſta
    0.64
    fromnode
    0.60
     NSCoder
    0.58
     queſta
    0.57
     ſol
    0.56
    帖最后由
    0.56
    Act Density 0.625%

    No Known Activations