© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92963
    Prev
    Next
    INDEX
    Explanations

    technical or medical text

    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
     garçons
    -0.48
     gué
    -0.36
    asa
    -0.35
     habis
    -0.35
    vaných
    -0.35
    GRANTED
    -0.35
    asi
    -0.35
    boys
    -0.35
    NewUrlParser
    -0.34
     bien
    -0.34
    POSITIVE LOGITS
    WebElementEntity
    0.81
    verwijspagina
    0.72
     مرئيه
    0.71
     photolibrary
    0.71
     समीक्षक
    0.71
    ])));
    0.69
     doubtnut
    0.69
     Efq
    0.68
     ModelExpression
    0.68
    المناصب
    0.67
    Activations Density 0.001%

    No Known Activations