© 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. 12086
    Prev
    Next
    INDEX
    Explanations

    references to tabular data structures or table-related elements in documents

    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
    prefixer
    -0.84
     Buxton
    -0.83
     ennemis
    -0.71
     للمعارف
    -0.69
     Bogen
    -0.68
     nemici
    -0.66
    loroethene
    -0.66
    conjunto
    -0.65
     fumée
    -0.65
     subtil
    -0.65
    POSITIVE LOGITS
     TD
    1.30
    TD
    1.26
     td
    0.99
     TDs
    0.87
    mtd
    0.78
    td
    0.74
     Towel
    0.69
    mpo
    0.68
     Folio
    0.65
    legi
    0.65
    Activations Density 0.004%

    No Known Activations