© 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. 20920
    Prev
    Next
    INDEX
    Explanations

    occurrences of technical terminology related to programming or data structures

    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
     Warwickshire
    -0.81
     Gine
    -0.76
    icoot
    -0.76
    requipa
    -0.75
    wickshire
    -0.70
     Artur
    -0.70
    ResponseData
    -0.70
     Polynesia
    -0.68
     Barbier
    -0.67
     Malone
    -0.66
    POSITIVE LOGITS
    tl
    1.13
     TL
    1.10
    TL
    1.09
     tl
    0.96
    ImageContext
    0.90
    BeginContext
    0.87
    EndInit
    0.86
    tling
    0.85
     LCS
    0.81
    awtextra
    0.78
    Activations Density 0.009%

    No Known Activations