© 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. 31902
    Prev
    Next
    INDEX
    Explanations

    specific version identifiers related to software or code repositories

    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
    titleMargin
    -0.63
     näch
    -0.57
    ThroughAttribute
    -0.57
    subprocess
    -0.55
    GraphicsUnit
    -0.54
    存知
    -0.53
     subprocess
    -0.52
     insuff
    -0.52
     mộc
    -0.52
    োগ
    -0.52
    POSITIVE LOGITS
    makeConstraints
    0.60
    ConstraintMaker
    0.59
    AlterField
    0.54
    tonsoft
    0.54
    !*\
    0.53
     normalidad
    0.50
     ویکی‌پدیا
    0.49
     viewType
    0.48
     makeStyles
    0.48
    достатки
    0.48
    Activations Density 0.002%

    No Known Activations