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. 20-CLT-HP
    4. 74020
    Prev
    Next
    INDEX
    Explanations

    technical/scientific texts

    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
    tagHelperRunner
    -1.05
     EconPapers
    -1.00
     disambiguazione
    -0.89
    interopRequire
    -0.85
    mybatisplus
    -0.81
    webElementXpaths
    -0.78
     unknownFields
    -0.77
    migrationBuilder
    -0.76
     AssemblyProduct
    -0.76
    ContentAsync
    -0.75
    POSITIVE LOGITS
    tes
    0.49
    adav
    0.45
    teva
    0.44
     PL
    0.42
     format
    0.41
     tre
    0.41
    zera
    0.41
     tour
    0.41
    ado
    0.40
    atri
    0.40
    Activations Density 0.001%

    No Known Activations