© 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. 10332
    Prev
    Next
    INDEX
    Explanations

    list

    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
     émissions
    -0.61
     scolaires
    -0.56
     erreurs
    -0.54
     réaliste
    -0.54
     médicaux
    -0.50
     vectorielles
    -0.50
     exámenes
    -0.50
     vectorielle
    -0.49
     calcetines
    -0.49
     plazos
    -0.49
    POSITIVE LOGITS
    Personensuche
    0.98
     المعيارى
    0.81
     hierogly
    0.77
     dunes
    0.73
     stratigraph
    0.70
     gulls
    0.70
    rungsseite
    0.70
     محفوظة
    0.69
    fromCharCode
    0.69
     snails
    0.69
    Activations Density 0.008%

    No Known Activations