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. 74343
    Prev
    Next
    INDEX
    Explanations

    technical and scientific jargon

    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
    MigrationBuilder
    -0.90
    Gas
    -0.90
     Gas
    -0.88
     surla
    -0.83
     feroit
    -0.83
    новниш
    -0.81
     avoient
    -0.80
     varandra
    -0.79
     gas
    -0.77
     GAS
    -0.77
    POSITIVE LOGITS
     Moq
    0.42
     FCC
    0.40
     ira
    0.38
    y
    0.36
    }{*}{
    0.36
     sar
    0.35
     Board
    0.34
     del
    0.34
     tamar
    0.34
    itect
    0.33
    Activations Density 0.165%

    No Known Activations