© 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. 22308
    Prev
    Next
    INDEX
    Explanations

    references to 'sheets' or related shapes in various 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
     Beards
    -0.89
     Prag
    -0.69
    underland
    -0.69
    TagMode
    -0.65
     Sear
    -0.63
    )?;
    -0.63
    گزاری
    -0.63
     attra
    -0.62
    Kristi
    -0.62
    dollis
    -0.61
    POSITIVE LOGITS
     sheets
    1.88
     Sheets
    1.85
     SHEET
    1.80
    Sheets
    1.73
     sheet
    1.72
    sheet
    1.68
    sheets
    1.67
     Sheet
    1.64
    Sheet
    1.62
    SHEET
    1.48
    Activations Density 0.009%

    No Known Activations