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. 74408
    Prev
    Next
    INDEX
    Explanations

    Portuguese text

    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
    rungsseite
    -0.81
    MigrationBuilder
    -0.78
    TagMode
    -0.75
    #+#
    -0.71
     صوتيه
    -0.71
    IUrlHelper
    -0.68
    $_['
    -0.65
    invokeLater
    -0.56
    titleMargin
    -0.55
    :+:
    -0.55
    POSITIVE LOGITS
    findpost
    0.66
     surla
    0.60
    uzen
    0.57
    ěstí
    0.52
    faden
    0.52
    entities
    0.50
     mixte
    0.49
    kkelen
    0.48
    dopodob
    0.48
     indifer
    0.48
    Activations Density 0.004%

    No Known Activations