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
    71
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    technical terms and concepts related to systems and structures in scientific contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Smarty
    -0.57
    httphttps
    -0.57
    $_['
    -0.56
     himo
    -0.50
    SequentialGroup
    -0.50
    WriteTagHelper
    -0.49
     Audiodateien
    -0.48
     nitrous
    -0.48
    redient
    -0.47
     Certifications
    -0.46
    POSITIVE LOGITS
     betweenstory
    0.52
    fromnode
    0.46
     utilization
    0.39
     structure
    0.35
     processes
    0.35
    ViewInit
    0.35
    ように
    0.35
    ValueStyle
    0.35
     factor
    0.34
     utilize
    0.34
    Act Density 0.052%

    No Known Activations