© 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. 18082
    Prev
    Next
    INDEX
    Explanations

    articles and quantifying terms in a text

    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
     mẽ
    -0.59
     Lazarus
    -0.58
     numberOfRows
    -0.57
    ViewFeatures
    -0.53
    зион
    -0.51
    unier
    -0.50
    :✨
    -0.49
    IDADES
    -0.49
     Lune
    -0.49
    ylla
    -0.49
    POSITIVE LOGITS
     Administrativna
    0.75
    contentLoaded
    0.73
     linkovi
    0.72
    featureID
    0.69
    Portale
    0.67
    expandindo
    0.66
    脚注の使い方
    0.62
    ContentAsync
    0.60
     />';
    0.58
    FunctionFlags
    0.58
    Activations Density 0.003%

    No Known Activations