© 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. 11477
    Prev
    Next
    INDEX
    Explanations

    Stevenson

    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
     Romana
    -0.95
     Stevenson
    -0.68
    newArrayList
    -0.51
    ileo
    -0.49
    NgModule
    -0.48
    ndig
    -0.48
    valg
    -0.48
    ViewChild
    -0.47
    ExecuteReader
    -0.47
    VELAND
    -0.47
    POSITIVE LOGITS
     disponibilités
    0.69
     CreateTagHelper
    0.66
    TagMode
    0.62
    mặt
    0.59
     lenker
    0.56
     חיצוניים
    0.56
     تضيفلها
    0.56
     ویکی‌پدیا
    0.56
    الدراسه
    0.54
    Demikian
    0.54
    Activations Density 0.015%

    No Known Activations