© 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. 93707
    Prev
    Next
    INDEX
    Explanations

    legal and code documents

    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
     legally
    -0.75
     officially
    -0.68
    officially
    -0.62
    legal
    -0.58
     legal
    -0.57
     lawfully
    -0.56
    ViewImports
    -0.56
     authorized
    -0.55
    放題
    -0.52
     Officially
    -0.52
    POSITIVE LOGITS
     الرياضيه
    0.82
     GetEnumerator
    0.73
    Nazionale
    0.71
     estimés
    0.70
     Wiktionnaire
    0.69
    CppMethod
    0.69
    saraba
    0.66
    SourceChecksum
    0.63
    出版年
    0.62
     Deceased
    0.61
    Activations Density 0.009%

    No Known Activations