© 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. 25934
    Prev
    Next
    INDEX
    Explanations

    symbols and structure related to programming or coding syntax

    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
    Not in Any Lists

    No Comments

    Negative Logits
    contentLoaded
    -0.75
    ⓧ
    -0.68
     urma
    -0.62
    ifred
    -0.59
    IVEREF
    -0.57
     TestBed
    -0.56
    ammans
    -0.56
    IsMutable
    -0.56
    umbersome
    -0.55
    oinette
    -0.55
    POSITIVE LOGITS
     minOccurs
    0.73
    <tr>
    0.71
    }")]
    0.62
    endcsname
    0.60
    }{*}{
    0.57
     Lati
    0.57
     uncertainty
    0.56
     roule
    0.56
     CACHE
    0.56
    arsal
    0.55
    Activations Density 0.003%

    No Known Activations