© 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. 22-RES-MATRYOSHKA-DC
    7. 3277
    Prev
    Next
    INDEX
    Explanations

    words and abbreviations related to scientific measurements and laboratory studies

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     propOrder
    -0.66
     Seligman
    -0.58
    setAccessible
    -0.58
    ➌
    -0.57
     تضيفلها
    -0.57
    ,:);
    -0.57
     متحده
    -0.57
     betweenstory
    -0.57
    maiden
    -0.56
    handleRequest
    -0.54
    POSITIVE LOGITS
     counts
    0.91
     count
    0.91
     counting
    0.86
    count
    0.84
     counted
    0.80
    Count
    0.80
    Counting
    0.80
     Counts
    0.79
     Count
    0.79
    counting
    0.79
    Activations Density 0.264%

    No Known Activations