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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1672
    Prev
    Next
    INDEX
    Explanations

    Java syntax code, especially curly braces and parentheses related to code blocks

    oai_token-act-pair · gemini-2.0-flash

    code symbols

    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
    tvguidetime
    -0.87
    verwijspagina
    -0.86
    -0.83
    ".
    
    -0.78
    GEBURTSDATUM
    -0.78
    IUrlHelper
    -0.78
    ,
    
    -0.75
    "),
    
    -0.73
    ).
    
    -0.73
     referenties
    -0.73
    POSITIVE LOGITS
    SuppressWarnings
    0.51
    constructor
    0.51
    mysqli
    0.48
    QtCore
    0.45
    return
    0.45
    valueOf
    0.45
    exe
    0.44
    ILogger
    0.44
    self
    0.44
    NSMutable
    0.43
    Activations Density 3.242%

    No Known Activations