© 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. 9974
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and structures, particularly those associated with function arguments and memory operations

    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
    tagHelperRunner
    -1.11
    出版年
    -0.73
    mybatisplus
    -0.72
    providedIn
    -0.71
     numberOfRows
    -0.71
    новниш
    -0.69
     cherchés
    -0.68
     cdti
    -0.67
    SizeF
    -0.67
    ✨:
    -0.66
    POSITIVE LOGITS
    CrossRef
    0.45
    顺序
    0.43
    getReference
    0.41
     közé
    0.41
     destra
    0.40
     mód
    0.40
     depan
    0.40
     TextAlign
    0.40
    PEZ
    0.40
     principalement
    0.40
    Activations Density 0.458%

    No Known Activations