© 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. 4-CLT-HP
    7. 80
    Prev
    Next
    INDEX
    Explanations

    all

    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
     classes
    -0.41
    зможно
    -0.38
    utilities
    -0.37
     Variable
    -0.36
    godic
    -0.36
     pinulongan
    -0.35
     Sea
    -0.34
     uuidv
    -0.34
     aang
    -0.34
    enoord
    -0.34
    POSITIVE LOGITS
     ویکی‌پدیا
    0.83
    awtextra
    0.81
    hyrchwyd
    0.79
     jScrollPane
    0.79
    RuleContext
    0.75
    \{\\
    0.73
     ujednoznacz
    0.73
    RectangleBorder
    0.72
    TagMode
    0.71
    parsedMessage
    0.71
    Activations Density 0.001%

    No Known Activations