© 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. 30500
    Prev
    Next
    INDEX
    Explanations

    references to version control actions related to Git commits

    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
    Havolalar
    -0.69
     Zar
    -0.68
     Lorenz
    -0.66
     Dara
    -0.65
    Hauptartikel
    -0.64
    Zar
    -0.63
     Nade
    -0.63
    فار
    -0.62
     Esau
    -0.60
    RAD
    -0.57
    POSITIVE LOGITS
     Commit
    1.38
     commit
    1.26
     COMMIT
    1.23
    commit
    1.20
     commits
    1.20
    Commit
    1.19
    commits
    1.12
     committed
    1.09
     committing
    1.08
     Committed
    0.96
    Activations Density 0.003%

    No Known Activations