Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 11065
    Prev
    Next
    INDEX
    Explanations

    USH

    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
    typeorm
    -0.56
    AddTagHelper
    -0.56
     estekak
    -0.56
    AndEndTag
    -0.52
    Tembelea
    -0.51
    herr
    -0.50
     podjela
    -0.50
     amb
    -0.49
    runApp
    -0.49
    entle
    -0.49
    POSITIVE LOGITS
    ing
    0.66
    ed
    0.62
    存于互联网档案馆
    0.61
    geving
    0.54
    Chham
    0.50
    quial
    0.48
    iness
    0.48
    sticks
    0.48
    ingan
    0.47
    ictwo
    0.46
    Activations Density 0.012%

    No Known Activations