© 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. 32562
    Prev
    Next
    INDEX
    Explanations

    clauses related to conditions and specifications in instructions or descriptions

    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
    Negative Logits
    findpost
    -0.57
    MockBean
    -0.51
     статистики
    -0.49
    DataColumn
    -0.46
     جغرافيا
    -0.46
    migrationBuilder
    -0.45
    ونز
    -0.45
    Географи
    -0.44
     hätte
    -0.44
     ویکی‌پدیای
    -0.44
    POSITIVE LOGITS
     defaults
    0.83
     Defaults
    0.70
     default
    0.68
     pinulongan
    0.64
     AssemblyCulture
    0.61
    ANDUM
    0.60
     Undefined
    0.59
     Crusoe
    0.59
    ukone
    0.58
    Defaults
    0.57
    Activations Density 0.223%

    No Known Activations