© 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. 22883
    Prev
    Next
    INDEX
    Explanations

    specific structural or coding elements in programming or data-related contexts

    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
     الحره
    -0.63
    tadır
    -0.62
     mergeFrom
    -0.61
     mijne
    -0.60
    říklad
    -0.58
     Wiktionnaire
    -0.58
    gaande
    -0.58
    */),
    -0.57
    достатки
    -0.57
    FunctionFlags
    -0.57
    POSITIVE LOGITS
     Dulce
    0.56
     sultan
    0.52
     BioLib
    0.51
     composed
    0.47
    apimachinery
    0.47
    хьтан
    0.47
    enterOuterAlt
    0.47
    Dtl
    0.46
     consists
    0.46
     crumbled
    0.46
    Activations Density 0.106%

    No Known Activations