© 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. 5-CLT-HP
    7. 97400
    Prev
    Next
    INDEX
    Explanations

    dose

    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
    tagHelperRunner
    -0.69
    ⓧ
    -0.69
     Audiodateien
    -0.69
    новниш
    -0.66
     HttpNotFound
    -0.62
    JspWriter
    -0.61
     Baillargeon
    -0.60
     Pairs
    -0.60
     चीज़ों
    -0.60
    queryInterface
    -0.59
    POSITIVE LOGITS
     equivalent
    0.66
    الحياه
    0.56
    equivalent
    0.55
     Equivalent
    0.54
     équi
    0.49
     equivalente
    0.49
     ویکی‌پدی
    0.47
     conversion
    0.47
     equivalents
    0.46
     conversión
    0.46
    Activations Density 0.004%

    No Known Activations