© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94942
    Prev
    Next
    INDEX
    Explanations

    lack

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPA
    -0.55
    CloseOperation
    -0.55
    essentiel
    -0.55
     supposes
    -0.54
     SEDS
    -0.53
    onets
    -0.52
     hooks
    -0.52
     NSCoder
    -0.50
     PARSER
    -0.49
    цездатний
    -0.49
    POSITIVE LOGITS
    <bos>
    0.68
     getItemId
    0.63
    ſelf
    0.59
     Reſ
    0.53
     houſe
    0.52
     purpoſe
    0.52
    doğan
    0.52
    ant
    0.51
     ease
    0.50
    volve
    0.49
    Activations Density 0.119%

    No Known Activations