© 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. 0-CLT-HP
    7. 94263
    Prev
    Next
    INDEX
    Explanations

    t

    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
     auroit
    -0.82
     noires
    -0.77
     storici
    -0.75
     étoit
    -0.73
     publiques
    -0.72
     fédé
    -0.72
     habet
    -0.72
     réguli
    -0.71
     médicaux
    -0.71
     rapides
    -0.70
    POSITIVE LOGITS
     الحره
    0.63
     buy
    0.63
     referenties
    0.62
     be
    0.59
     dig
    0.58
     get
    0.57
    المناصب
    0.57
     ویکی‌پدیا
    0.57
    ̸
    0.57
     expect
    0.56
    Activations Density 0.053%

    No Known Activations