© 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. 23867
    Prev
    Next
    INDEX
    Explanations

    terminology related to grammar in programming languages

    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
    IndentedString
    -0.93
    mobileqq
    -0.88
    InvalidProtocol
    -0.79
    LabelTagHelper
    -0.75
     AssemblyProduct
    -0.75
    apimachinery
    -0.72
    atteindre
    -0.72
     Völ
    -0.71
     Bene
    -0.71
     Eilish
    -0.69
    POSITIVE LOGITS
     Grammar
    1.48
     grammar
    1.47
    Grammar
    1.46
    grammar
    1.38
     gramm
    1.12
     grammatical
    0.85
     GRAM
    0.74
    antlr
    0.72
     Gramm
    0.71
     English
    0.67
    Activations Density 0.002%

    No Known Activations