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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40736
    Prev
    Next
    INDEX
    Explanations

    stories

    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
    NamedQuery
    -0.56
     crossings
    -0.52
    RetentionPolicy
    -0.52
    inguém
    -0.50
     חיצוניים
    -0.49
     war
    -0.48
    >(_
    -0.48
     مشين
    -0.47
    begre
    -0.47
     furrows
    -0.47
    POSITIVE LOGITS
    yntaxException
    0.73
    tadır
    0.63
    новниш
    0.59
    ("}");
    0.58
    <bos>
    0.57
     Meksiku
    0.56
    !*\
    0.55
     समीक्षक
    0.54
    webElementXpaths
    0.52
    ftagPool
    0.52
    Activations Density 0.095%

    No Known Activations