© 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. 5-CLT-HP
    7. 5027
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    zulegen
    -0.56
    إنه
    -0.54
     it
    -0.48
     any
    -0.48
    ClInclude
    -0.48
    flexDirection
    -0.47
    lepiej
    -0.47
     сравнению
    -0.46
     no
    -0.45
    พวก
    -0.45
    POSITIVE LOGITS
    ValueStyle
    0.94
    SourceChecksum
    0.84
     resourceCulture
    0.83
    +#+
    0.83
     للمعارف
    0.83
    webElementXpaths
    0.77
     ligiloj
    0.77
    NameInMap
    0.75
    جغرافيا
    0.75
     Wikimedijinoj
    0.74
    Activations Density 0.003%

    No Known Activations