© 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. 12124
    Prev
    Next
    INDEX
    Explanations

    tokens representing whitespace or typographic characters

    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
     disponibilités
    -0.95
     typelib
    -0.79
     contextLoads
    -0.78
     chi̍t
    -0.77
     Paglinawan
    -0.75
    makeConstraints
    -0.73
    ftagPool
    -0.73
     StringTokenizer
    -0.72
     ویکی‌پدی
    -0.71
    DataAnnotations
    -0.70
    POSITIVE LOGITS
    Cfg
    1.56
     cfg
    0.88
    cfg
    0.82
    CFG
    0.59
    EndGlobalSection
    0.56
    ={\
    0.50
     configuration
    0.48
    ыре
    0.48
    AppConfig
    0.47
    ình
    0.46
    Activations Density 0.000%

    No Known Activations