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. 0-CLT-HP
    4. 40912
    Prev
    Next
    INDEX
    Explanations

    students

    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
     Paglinawan
    -0.80
     noDo
    -0.70
    frastructure
    -0.68
    WriteTagHelper
    -0.68
    __).
    -0.67
    ALLENG
    -0.65
    ficulty
    -0.63
     للاسماء
    -0.63
    mended
    -0.62
    addGap
    -0.62
    POSITIVE LOGITS
     LoggerFactory
    0.52
     vouloir
    0.44
     Questi
    0.44
     measurement
    0.44
    be
    0.43
     of
    0.43
    not
    0.43
     Leurs
    0.43
     OMITBAD
    0.43
     Celui
    0.42
    Activations Density 0.008%

    No Known Activations