© 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. 5-CLT-HP
    7. 92478
    Prev
    Next
    INDEX
    Explanations

    punctuation and spelling

    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
    remes
    -0.53
    CloseOperation
    -0.50
    tagext
    -0.48
    ceng
    -0.47
     StatefulWidget
    -0.47
     Cah
    -0.45
    guten
    -0.45
    ן
    -0.44
    ICTS
    -0.44
    alten
    -0.44
    POSITIVE LOGITS
    prep
    0.63
    FunctionFlags
    0.63
    ModelSerializer
    0.62
    MigrationBuilder
    0.60
    pertino
    0.59
    SOUNDBITE
    0.59
    perty
    0.57
    enschappe
    0.57
    ⓧ
    0.57
     originaux
    0.56
    Activations Density 0.000%

    No Known Activations