© 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. 0-CLT-HP
    7. 43740
    Prev
    Next
    INDEX
    Explanations

    canvas

    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
    parsedMessage
    -0.76
    CloseOperation
    -0.72
    ArrowToggle
    -0.69
    IVEREF
    -0.68
    ंदीखरीदारी
    -0.67
     canvas
    -0.63
     ProtoMessage
    -0.62
    下载附件
    -0.62
    GEBURTSDATUM
    -0.61
    Slf
    -0.60
    POSITIVE LOGITS
    ing
    0.79
    a
    0.79
    ed
    0.77
    es
    0.75
     himſelf
    0.72
     itſelf
    0.65
    otic
    0.64
     myſelf
    0.62
    unciation
    0.59
    iC
    0.59
    Activations Density 0.417%

    No Known Activations