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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11503
    Prev
    Next
    INDEX
    Explanations

    the definite article "the" in proximity to various nouns and terms

    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
    AsUp
    -0.69
    webElementXpaths
    -0.66
    HasBeenSet
    -0.64
    SharedCtor
    -0.61
    Tembelea
    -0.60
     BoxDecoration
    -0.57
    queryInterface
    -0.55
    sizeCache
    -0.54
    исленность
    -0.54
    yntaxException
    -0.52
    POSITIVE LOGITS
     المعيارى
    0.81
     مشين
    0.79
     iniziale
    0.57
     препратки
    0.56
    ฐ
    0.56
    }{|
    0.54
     wikipagina
    0.54
     needed
    0.53
    Fernsehserie
    0.53
    ISupport
    0.53
    Activations Density 0.094%

    No Known Activations