© 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. 1-CLT-HP
    7. 15455
    Prev
    Next
    INDEX
    Explanations

    Names

    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
     Johnson
    -1.13
    Johnson
    -0.98
     Davis
    -0.89
     JOHNSON
    -0.85
     johnson
    -0.82
    johnson
    -0.75
    Davis
    -0.70
     Smith
    -0.64
     DAVIS
    -0.64
     Johnston
    -0.59
    POSITIVE LOGITS
    enumi
    0.78
     للاسماء
    0.70
    ympto
    0.68
    FieldBuilder
    0.68
    ScopeManager
    0.66
    Fordítás
    0.65
     HttpNotFound
    0.64
    EndInit
    0.63
     tartalomajánló
    0.63
     فريبيس
    0.62
    Activations Density 0.008%

    No Known Activations