© 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. 20-CLT-HP
    7. 74448
    Prev
    Next
    INDEX
    Explanations

    Technical descriptions/lists

    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
    +#+
    -0.78
    PreferredItem
    -0.74
     Réponses
    -0.64
    ViewImports
    -0.63
     Couleur
    -0.59
     indisponible
    -0.57
    клопе
    -0.56
    zerland
    -0.56
    UnusedPrivate
    -0.55
    PerformLayout
    -0.54
    POSITIVE LOGITS
    ThroughAttribute
    0.56
    rfc
    0.47
     fact
    0.47
     box
    0.43
     NSCoder
    0.42
     alternative
    0.42
     cast
    0.41
     gouvernements
    0.41
     step
    0.40
     factor
    0.40
    Activations Density 0.001%

    No Known Activations