© 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. 0-CLT-HP
    7. 94451
    Prev
    Next
    INDEX
    Explanations

    construction, architecture

    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
    loroethane
    -0.46
    LLocation
    -0.46
    saraba
    -0.45
     {}));
    -0.45
    ThroughAttribute
    -0.43
    Ecotoxicity
    -0.42
    最快更新
    -0.41
    kfree
    -0.41
    nsec
    -0.41
    glEnd
    -0.40
    POSITIVE LOGITS
    SuppressLint
    0.63
    MENAFN
    0.63
    :+:
    0.60
     Hebrews
    0.59
    astify
    0.59
    helves
    0.56
     Trapp
    0.56
     الاطلاع
    0.56
     Euph
    0.55
    </table>
    0.54
    Activations Density 0.036%

    No Known Activations