© 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. 1639
    Prev
    Next
    INDEX
    Explanations

    industrial, medical, career contexts

    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
    RectangleBorder
    -0.85
    ButterKnife
    -0.70
    üyük
    -0.69
    anyak
    -0.66
    reportWebVitals
    -0.64
    sidemargin
    -0.64
    DebuggerNonUser
    -0.63
    GraphicsUnit
    -0.63
    MessageOf
    -0.63
    contiguous
    -0.62
    POSITIVE LOGITS
    <bos>
    0.75
    s
    0.56
    ی
    0.55
     Paglinawan
    0.48
    ↵↵
    0.45
    ing
    0.42
     spot
    0.42
    Autoritní
    0.42
    baomidou
    0.41
    edly
    0.41
    Activations Density 0.229%

    No Known Activations