© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 6091
    Prev
    Next
    INDEX
    Explanations

    computers and technology

    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
    Negative Logits
    uolo
    -0.52
     הז
    -0.50
    richTextPanel
    -0.50
    setDo
    -0.49
    govine
    -0.48
     prétend
    -0.48
    HtmlAttribute
    -0.46
    Gizmos
    -0.45
    hazi
    -0.45
    altezza
    -0.44
    POSITIVE LOGITS
     NUKAT
    0.72
     يتيمه
    0.62
    rungsseite
    0.56
     ویکی‌پدیا
    0.55
    BuilderFactory
    0.55
     Eſ
    0.54
     Efq
    0.52
    createClass
    0.52
     enterprise
    0.51
     Reſ
    0.50
    Activations Density 0.002%

    No Known Activations