© 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. 90580
    Prev
    Next
    INDEX
    Explanations

    Dye

    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
    s
    -0.82
    ی
    -0.77
    a
    -0.75
    i
    -0.70
    e
    -0.69
    y
    -0.68
    er
    -0.65
    o
    -0.64
    an
    -0.62
     rubs
    -0.58
    POSITIVE LOGITS
    posedge
    0.60
    oredCriteria
    0.58
    ună
    0.57
     ویکی‌پدیای
    0.56
    ├──
    0.54
    kloped
    0.54
    لكتر
    0.52
    grà
    0.51
    teddy
    0.50
    Soorten
    0.50
    Activations Density 0.814%

    No Known Activations