Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16345
    Prev
    Next
    INDEX
    Explanations

    conjunctions, pronouns, and medical/legal terms or discussions

    oai_token-act-pair · gemini-2.0-flash

    unclear, possibly OCR errors

    np_token-act-pair-logits · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_16/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
     étu
    -0.56
    RegressionTest
    -0.53
     investigation
    -0.52
     studied
    -0.49
     étudier
    -0.49
     studying
    -0.49
     ostavi
    -0.48
     investigated
    -0.48
    investigation
    -0.48
     int
    -0.48
    POSITIVE LOGITS
     تانيه
    0.73
     كومونز
    0.68
    \{\\
    0.66
     שוליים
    0.65
     оригіналу
    0.62
    InvalidProtocol
    0.57
     INVENTION
    0.57
    mota
    0.56
    ContentAlignment
    0.56
    LLocation
    0.56
    Activations Density 2.924%

    No Known Activations