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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 2-GEMMASCOPE-TRANSCODER-16K
    4. 14197
    Prev
    Next
    INDEX
    Explanations

    text relating to the death penalty, punishment, and the legal system in general

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_2/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    makeConstraints
    -1.11
     MainAxisSize
    -0.85
     snippetHide
    -0.73
    CloseOperation
    -0.72
    DockStyle
    -0.70
    InputBorder
    -0.70
     فريبيس
    -0.69
    WithMany
    -0.69
    AnimationsModule
    -0.68
     penalty
    -0.68
    POSITIVE LOGITS
    <bos>
    0.93
     szív
    0.51
    ">//
    0.51
     hafif
    0.50
     hű
    0.49
     juos
    0.48
    uoja
    0.47
    あんな
    0.47
     öyle
    0.46
     doskona
    0.46
    Activations Density 7.462%

    No Known Activations