© 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. 0-CLT-HP
    7. 41326
    Prev
    Next
    INDEX
    Explanations

    was

    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
     Juifs
    -0.65
     rayures
    -0.65
     prêtres
    -0.64
     prisonniers
    -0.63
     preuves
    -0.63
     scolaires
    -0.62
     émissions
    -0.62
     élas
    -0.58
     cérami
    -0.58
     représentants
    -0.58
    POSITIVE LOGITS
     nahilalakip
    0.73
     Chosen
    0.66
    djangoproject
    0.65
     chosen
    0.64
    RunAsync
    0.59
    ApiModel
    0.58
     الحره
    0.58
     للاسماء
    0.58
    UObject
    0.57
     незавершена
    0.57
    Activations Density 0.072%

    No Known Activations