© 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. 32475
    Prev
    Next
    INDEX
    Explanations

    code-related constructs, particularly those involving buffer and writer operations

    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
    styleType
    -0.61
    OGND
    -0.56
    atimes
    -0.53
    RectangleBorder
    -0.52
    sikal
    -0.52
    writerow
    -0.50
    parsedMessage
    -0.50
    ulite
    -0.50
    TargetApi
    -0.49
    cipar
    -0.48
    POSITIVE LOGITS
     StatefulWidget
    0.60
    eseorang
    0.54
     فريبيس
    0.54
     Económica
    0.54
     elective
    0.52
    errHandler
    0.52
    iastical
    0.51
     Stirn
    0.50
    еро
    0.49
     exh
    0.49
    Activations Density 0.016%

    No Known Activations