© 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. 1-CLT-HP
    7. 10874
    Prev
    Next
    INDEX
    Explanations

    story

    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
    usercontent
    -0.59
    colgroup
    -0.59
    ValueStyle
    -0.56
    contentPadding
    -0.52
     giản
    -0.46
    <()>
    -0.45
    первых
    -0.44
    sizeCache
    -0.43
    ::~
    -0.42
    HostException
    -0.42
    POSITIVE LOGITS
    :✨
    0.61
    SharedDtor
    0.61
     Kesehatan
    0.57
     Италијани
    0.56
     Million
    0.53
     contextLoads
    0.53
     Banks
    0.53
     الرياضيه
    0.52
    Banks
    0.52
     ErrIntOverflow
    0.52
    Activations Density 0.004%

    No Known Activations