© 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. 26744
    Prev
    Next
    INDEX
    Explanations

    concepts related to mathematical definitions and properties, particularly in the context of probability and statistics

    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
    Datuak
    -1.15
     AssemblyProduct
    -0.87
    +#+#
    -0.73
    setVerticalGroup
    -0.69
    sizeCache
    -0.68
    loroethene
    -0.65
    migrationBuilder
    -0.64
     EconPapers
    -0.64
    MigrationBuilder
    -0.62
    (__('
    -0.62
    POSITIVE LOGITS
    breviations
    0.48
    Cyfarwyddwr
    0.46
    存于互联网档案馆
    0.45
    glLoad
    0.45
    پاسخ
    0.43
     kapcsolat
    0.43
    webElement
    0.42
     numerus
    0.41
    umbuhan
    0.41
     transferência
    0.41
    Activations Density 0.012%

    No Known Activations