© 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. 20388
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical connections and properties within algebraic structures

    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
     propOrder
    -0.93
    WebElementEntity
    -0.80
     ivelany
    -0.79
    GEBURTSDATUM
    -0.79
     ویکی‌پدی
    -0.78
    tagHelperRunner
    -0.73
    msgTypes
    -0.73
    SharedDtor
    -0.72
    脚注の使い方
    -0.71
    webElementGuid
    -0.71
    POSITIVE LOGITS
    moveToFirst
    0.51
    <?,
    0.46
    ΐ
    0.44
     Segovia
    0.41
    ICTO
    0.41
    dide
    0.40
     turn
    0.40
    OSA
    0.39
     discoveries
    0.39
     ect
    0.39
    Activations Density 0.136%

    No Known Activations