© 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. 25299
    Prev
    Next
    INDEX
    Explanations

    syntax elements and markers in code

    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
     itſelf
    -1.28
     Theſe
    -1.28
     Monfieur
    -1.16
     Jefus
    -1.15
     Houſe
    -1.15
     himſelf
    -1.09
     houſe
    -1.09
     Majefty
    -1.08
     Reſ
    -1.07
     Efq
    -1.07
    POSITIVE LOGITS
     Thomas
    0.62
     Al
    0.58
     <
    0.57
     et
    0.55
    ///<
    0.55
    opsis
    0.54
    subplot
    0.54
     Ar
    0.54
     En
    0.52
    ElementException
    0.52
    Activations Density 0.001%

    No Known Activations