© 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. 4-CLT-HP
    7. 1846
    Prev
    Next
    INDEX
    Explanations

    problems or issues

    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
    runApp
    -0.59
     responsibility
    -0.55
    >{"
    -0.50
    />
    -0.50
     proceedings
    -0.49
    responsibility
    -0.48
    ]<=
    -0.48
    '])){
    -0.47
    WithMany
    -0.47
     astore
    -0.47
    POSITIVE LOGITS
    modb
    0.62
     Protobuf
    0.59
    ArrowToggle
    0.59
    RuleContext
    0.57
    Tikang
    0.56
     تضيفلها
    0.55
    riwal
    0.54
    uttori
    0.54
    出版年
    0.54
    URLException
    0.54
    Activations Density 0.002%

    No Known Activations