© 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. 8950
    Prev
    Next
    INDEX
    Explanations

    references to a "sleeve" in various contexts related to wire organization

    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
     الرياضيه
    -0.78
     Donat
    -0.76
    Хьажоргаш
    -0.73
     Rhi
    -0.71
     Rhonda
    -0.69
    permalink
    -0.68
    రం
    -0.68
     Gemein
    -0.67
     stic
    -0.66
     halluc
    -0.65
    POSITIVE LOGITS
     Sleeve
    1.67
     sleeve
    1.65
     sleeves
    1.63
    Sleeve
    1.57
    sleeve
    1.56
     Sleeves
    1.48
    leeve
    1.30
    Slee
    1.23
    slee
    1.13
     SLE
    1.03
    Activations Density 0.002%

    No Known Activations