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. 22-CLT-HP
    4. 74447
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act-logits · 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
     initComponents
    -0.90
    GOTREF
    -0.83
    ----</
    -0.79
    GEBURTSDATUM
    -0.75
    TypedDataSet
    -0.75
    TagMode
    -0.73
    setupUi
    -0.72
    -------------</
    -0.72
    fjspx
    -0.71
    PRNewswire
    -0.71
    POSITIVE LOGITS
    conv
    0.45
    Box
    0.45
    zii
    0.44
    Bus
    0.44
    al
    0.43
    сия
    0.43
     vol
    0.41
    Con
    0.41
    app
    0.40
    tagHelper
    0.40
    Activations Density 0.002%

    No Known Activations