© 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. 20-CLT-HP
    7. 72245
    Prev
    Next
    INDEX
    Explanations

    Foreign language

    np_max-act-logits · 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
     descu
    -0.40
    ekan
    -0.39
    tyg
    -0.39
     furi
    -0.38
     Castig
    -0.38
    CLAIMER
    -0.38
    quelize
    -0.37
    Buildable
    -0.37
    Bindable
    -0.37
    ters
    -0.37
    POSITIVE LOGITS
     الحره
    0.82
    migrationBuilder
    0.78
     EconPapers
    0.77
     ExecuteAsync
    0.77
    脚注の使い方
    0.77
     pinulongan
    0.74
    ंदीखरीदारी
    0.73
    \{\\
    0.71
     الوطنيه
    0.70
    MigrationBuilder
    0.69
    Activations Density 0.000%

    No Known Activations