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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1749
    Prev
    Next
    INDEX
    Explanations

    content related to mathematical or physics papers, especially concerning renormalization, gauge theories, and dimensional regularization

    oai_token-act-pair · gemini-2.0-flash

    Theoretical physics papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     InputDecoration
    -0.74
    MLLoader
    -0.71
    queryInterface
    -0.61
    migrationBuilder
    -0.57
    存于互联网档案馆
    -0.57
    ReusableCell
    -0.55
     ModelExpression
    -0.55
    ImageField
    -0.53
     onPostExecute
    -0.53
     thiệu
    -0.53
    POSITIVE LOGITS
    +#+
    0.66
    SourceChecksum
    0.57
     '\\;'
    0.53
     EconPapers
    0.50
     teaching
    0.49
     Yao
    0.49
    acias
    0.48
    Teaching
    0.47
    ventions
    0.47
    ingue
    0.47
    Activations Density 8.659%

    No Known Activations