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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 21641
    Prev
    Next
    INDEX
    Explanations

    programming language syntax elements, specifically related to variable declarations and assignments

    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
    ритори
    -0.81
     EconPapers
    -0.69
    FunctionFlags
    -0.69
    İstinadlar
    -0.66
    Portail
    -0.64
    findpost
    -0.64
    AnchorStyles
    -0.62
     initComponents
    -0.62
     समीक्षाएं
    -0.61
     يتيمه
    -0.60
    POSITIVE LOGITS
    $__
    0.74
     насељу
    0.60
    atihan
    0.54
    addCriterion
    0.49
    rollment
    0.47
     einzu
    0.47
    uscular
    0.47
    GetAxis
    0.46
    quio
    0.46
    Биография
    0.46
    Activations Density 0.003%

    No Known Activations