© 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. 17062
    Prev
    Next
    INDEX
    Explanations

    commands and syntax related to code execution and modification in programming or scripting environments

    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
    فایل‌لار
    -0.66
    pholes
    -0.64
     Reſ
    -0.63
     ſind
    -0.58
     Conſ
    -0.58
     Anſ
    -0.57
     Kund
    -0.57
     Diſ
    -0.57
     Gim
    -0.55
     airst
    -0.55
    POSITIVE LOGITS
     للمعارف
    0.68
    󠁿
    0.68
     grep
    0.67
    grep
    0.65
     nakalista
    0.65
     mergeFrom
    0.63
    }');
    0.63
     )}$
    0.62
    Население
    0.60
    reihe
    0.59
    Activations Density 0.026%

    No Known Activations