© 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. 72820
    Prev
    Next
    INDEX
    Explanations

    Produce

    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
    ResumeLayout
    -0.53
    Istorija
    -0.47
    жни
    -0.46
    XmlType
    -0.45
    Zed
    -0.44
    Emin
    -0.44
    株
    -0.44
    ợ
    -0.44
    zus
    -0.43
    AutoScaleMode
    -0.43
    POSITIVE LOGITS
     estimés
    0.66
    Hozzáférés
    0.63
     quarter
    0.59
    rrggbb
    0.59
     trajets
    0.58
     Quarter
    0.58
     الدولى
    0.57
     Италијани
    0.54
    ハーフ
    0.54
    Personensuche
    0.54
    Activations Density 0.000%

    No Known Activations