© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 15225
    Prev
    Next
    INDEX
    Explanations

    code structures and control flow elements 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
    ArgsConstructor
    -0.93
     kasarigan
    -0.82
     ujednoznacz
    -0.77
     disambiguazione
    -0.73
     EconPapers
    -0.69
     ExecuteAsync
    -0.69
     &___
    -0.68
    ValueGenerated
    -0.68
    ActionCreators
    -0.67
    queryInterface
    -0.67
    POSITIVE LOGITS
     terakhir
    0.50
     poslední
    0.44
     still
    0.42
     last
    0.41
     sarili
    0.41
    最后一个
    0.40
     final
    0.40
     mieć
    0.39
    finalize
    0.39
    <eos>
    0.39
    Activations Density 0.038%

    No Known Activations