Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 67
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to statistical analysis and clinical outcomes

    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
     виправивши
    -0.69
    mybatisplus
    -0.56
    ikin
    -0.49
    section
    -0.48
    pertory
    -0.47
    ghe
    -0.47
    ']}
    -0.47
     चुनें
    -0.47
    ipot
    -0.46
    uml
    -0.45
    POSITIVE LOGITS
    Демографія
    0.90
    QMetaType
    0.68
    MigrationBuilder
    0.63
    ificance
    0.62
     AssemblyCulture
    0.61
    UnitTesting
    0.60
     declarat
    0.59
     bales
    0.59
     statistically
    0.58
     propOrder
    0.58
    Activations Density 3.147%

    No Known Activations