© 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. 5-CLT-HP
    7. 3006
    Prev
    Next
    INDEX
    Explanations

    Biographical numbers/dates

    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
    ricular
    -0.51
     folgendes
    -0.50
     AssemblyProduct
    -0.49
     EClass
    -0.49
    ErrUnexpectedEOF
    -0.49
     gewöhnlich
    -0.48
    lijken
    -0.48
    criptures
    -0.48
    untungan
    -0.47
    íncia
    -0.46
    POSITIVE LOGITS
    writeFieldEnd
    0.60
     Administrativna
    0.56
    IntoConstraints
    0.55
    migrationBuilder
    0.53
    الإنجليزية
    0.53
    Count
    0.50
    webElementXpaths
    0.50
    PreferredItem
    0.49
    例文帳に追加
    0.49
    $_['
    0.49
    Activations Density 0.003%

    No Known Activations