© 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. 95281
    Prev
    Next
    INDEX
    Explanations

    medical/scientific texts

    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
     purpoſe
    -0.84
     Efq
    -0.79
     reaſon
    -0.73
    ips
    -0.69
     Reſ
    -0.69
     ſta
    -0.68
     Monfieur
    -0.68
    ształ
    -0.66
     تضيفلها
    -0.66
    зулта
    -0.64
    POSITIVE LOGITS
    EndContext
    0.57
     of
    0.56
    addPreferredGap
    0.50
    mappedBy
    0.50
    Conclusions
    0.49
    openSession
    0.47
     Terme
    0.47
    setVerticalGroup
    0.46
     geslacht
    0.44
    CloseHandle
    0.43
    Activations Density 1.059%

    No Known Activations