© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2514
    Prev
    Next
    INDEX
    Explanations

    to

    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
    Use
    -0.56
    Adopt
    -0.50
    HAVE
    -0.50
    usage
    -0.48
    Apply
    -0.48
     Use
    -0.48
    DockStyle
    -0.46
    Ap
    -0.45
    use
    -0.45
     usage
    -0.45
    POSITIVE LOGITS
     '\\;'
    0.84
    expandindo
    0.77
    tagext
    0.68
    principalTable
    0.66
     otomatig
    0.66
    ształ
    0.66
     فريبيس
    0.65
    loroethane
    0.65
    DoubleQuotes
    0.64
    aarrggbb
    0.61
    Activations Density 0.002%

    No Known Activations