© 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. 15674
    Prev
    Next
    INDEX
    Explanations

    mathematics

    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
    Хьажоргаш
    -0.75
    ReusableCell
    -0.71
    Personensuche
    -0.70
    sizeCache
    -0.65
     AssemblyVersion
    -0.62
     تضيفلها
    -0.62
     ModelExpression
    -0.60
     الرياضيه
    -0.60
     الاطلاع
    -0.60
     ainfi
    -0.59
    POSITIVE LOGITS
     Kul
    0.57
    íqu
    0.54
    ceptre
    0.52
    esgue
    0.52
     responding
    0.52
    schild
    0.52
     fibres
    0.50
    ScopeManager
    0.50
     fibre
    0.48
    endpush
    0.48
    Activations Density 0.163%

    No Known Activations