© 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. 5-CLT-HP
    7. 98035
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    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
    RenderAtEndOf
    -0.66
    ImageContext
    -0.57
    ritation
    -0.57
     chande
    -0.55
    تقاوى
    -0.54
    ThroughAttribute
    -0.53
     Pula
    -0.51
     الرياضيه
    -0.51
     DbSet
    -0.50
    QMetaType
    -0.50
    POSITIVE LOGITS
    rungsseite
    0.50
    )(-
    0.49
     StatefulWidget
    0.48
    Véxase
    0.47
    inalg
    0.46
    geven
    0.46
    QUADS
    0.46
     Вікіпе
    0.46
     enged
    0.46
     faced
    0.45
    Activations Density 0.021%

    No Known Activations