© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5939
    Prev
    Next
    INDEX
    Explanations

    preprocessor include directives, especially those involving boost library headers

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    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
    sizeCache
    -0.69
     '\\;'
    -0.66
    webElementXpaths
    -0.63
     Himo
    -0.58
    <bos>
    -0.57
    SourceChecksum
    -0.57
     {?>
    -0.56
    דש
    -0.55
    numerusform
    -0.55
    enterOuterAlt
    -0.54
    POSITIVE LOGITS
     kaynağından
    0.73
     surla
    0.57
    ]--;
    0.56
    ViewStyle
    0.56
    InteropServices
    0.55
     afloat
    0.55
    ruptedException
    0.55
    parseDouble
    0.55
    criture
    0.54
    netinet
    0.54
    Activations Density 0.018%

    No Known Activations