© 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. 28680
    Prev
    Next
    INDEX
    Explanations

    technical terms and keywords related to programming and coding contexts

    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
     myſelf
    -0.77
     pleaſure
    -0.72
     Приступљено
    -0.68
     تضيفلها
    -0.66
     itſelf
    -0.66
     Anſ
    -0.65
    ICAGO
    -0.65
    Czytaj
    -0.64
     Diſ
    -0.64
     faſt
    -0.64
    POSITIVE LOGITS
    CodeAttribute
    0.60
     useDispatch
    0.54
     useAppContext
    0.52
    AndEndTag
    0.52
    WarningLevel
    0.51
    yarnpkg
    0.50
    Reducers
    0.49
     cherchés
    0.48
    mybatisplus
    0.48
    Filmographie
    0.48
    Activations Density 0.023%

    No Known Activations