© 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. 20-CLT-HP
    7. 71713
    Prev
    Next
    INDEX
    Explanations

    Code or technical documentation

    np_max-act-logits · 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
    tagHelperRunner
    -0.84
    出版年
    -0.82
    RenderAtEndOf
    -0.82
     Numerade
    -0.74
    はじめに
    -0.71
    SourceChecksum
    -0.70
    MLLoader
    -0.70
    UrlResolution
    -0.69
    aarrggbb
    -0.68
     resourceCulture
    -0.67
    POSITIVE LOGITS
     myſelf
    0.43
    inputType
    0.42
     pupil
    0.38
     '
    0.37
     ſeveral
    0.36
    taj
    0.35
    rints
    0.35
    empt
    0.35
    axel
    0.34
    daille
    0.34
    Activations Density 0.001%

    No Known Activations