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-GEMMASCOPE-TRANSCODER-16K
    4. 14174
    Prev
    Next
    INDEX
    Explanations

    text in Spanish related to SQL database operations and javascript functions

    oai_token-act-pair · gemini-2.0-flash

    Non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/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
     hers
    -0.73
     Ours
    -0.62
     theirs
    -0.59
     ་་
    -0.58
    Aluno
    -0.56
     ours
    -0.56
     therewith
    -0.56
    Ours
    -0.56
     doubtnut
    -0.56
     ―――――
    -0.54
    POSITIVE LOGITS
     JsonResult
    0.49
    quio
    0.48
    parsedMessage
    0.47
    HttpPut
    0.47
     raya
    0.47
     disambiguazione
    0.43
    oosevelt
    0.41
     McClure
    0.41
    rewsbury
    0.41
    شهاد
    0.41
    Activations Density 0.348%

    No Known Activations