© 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. 4-CLT-HP
    7. 1569
    Prev
    Next
    INDEX
    Explanations

    asking questions

    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
     several
    -0.42
     feveral
    -0.40
    affiche
    -0.38
     Spend
    -0.38
     tuturor
    -0.38
     tất
    -0.37
     EVERYTHING
    -0.37
     EVERY
    -0.37
     spend
    -0.37
    HtmlAttribute
    -0.37
    POSITIVE LOGITS
    <bos>
    0.90
     Infórmanos
    0.82
     disambiguazione
    0.73
    HasForeignKey
    0.72
    principalTable
    0.71
     whether
    0.71
    whether
    0.70
    
    0.70
    ftagPool
    0.69
    ofType
    0.68
    Activations Density 0.039%

    No Known Activations