© 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. 72078
    Prev
    Next
    INDEX
    Explanations

    Archived information, colons

    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
     Wikimedijinoj
    -0.79
    addCriterion
    -0.76
    tvguidetime
    -0.73
     ویکی‌پدیای
    -0.73
    évaluateur
    -0.71
    ANTLR
    -0.69
    RUnlock
    -0.68
    Tikang
    -0.66
    EndGlobalSection
    -0.66
    tagext
    -0.65
    POSITIVE LOGITS
     Independence
    0.45
    matan
    0.45
    ns
    0.43
     adik
    0.42
     независи
    0.42
     Ivy
    0.41
    versing
    0.41
     Tri
    0.41
    NS
    0.41
    izable
    0.40
    Activations Density 0.003%

    No Known Activations