© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 15768
    Prev
    Next
    INDEX
    Explanations

    code structure elements and AST (Abstract Syntax Tree) components in programming

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     estimés
    -0.62
    ContentAsync
    -0.61
    преки
    -0.61
    MENAFN
    -0.60
     milieux
    -0.59
     smtplib
    -0.59
    Referências
    -0.57
    WarningLevel
    -0.54
    Portail
    -0.53
    ConverterFactory
    -0.53
    POSITIVE LOGITS
    nodeType
    0.57
    abestanden
    0.54
     ویکی‌پدیای
    0.53
    sizeCache
    0.50
    RuleContext
    0.49
    moveToFirst
    0.49
     berusia
    0.48
     läm
    0.48
    ASTNode
    0.47
     root
    0.46
    Activations Density 0.071%

    No Known Activations