© 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. 97510
    Prev
    Next
    INDEX
    Explanations

    health

    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
     Paglinawan
    -0.90
    تقاوى
    -0.89
    MigrationBuilder
    -0.84
     disambiguazione
    -0.83
    parsedMessage
    -0.82
    脚注の使い方
    -0.81
    发表于
    -0.81
    SharedDtor
    -0.79
     surla
    -0.79
    <bos>
    -0.78
    POSITIVE LOGITS
     uomini
    0.43
    Invoker
    0.41
     or
    0.40
    ison
    0.40
    h
    0.40
    畳
    0.40
     your
    0.39
    renza
    0.38
    ru
    0.38
    mum
    0.38
    Activations Density 0.008%

    No Known Activations