© 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. 10698
    Prev
    Next
    INDEX
    Explanations

    elements of mathematical notation or references to variables and equations

    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
    SourceChecksum
    -0.74
     &___
    -0.66
    CppMethod
    -0.64
    exitRule
    -0.63
    asteroide
    -0.62
    TagMode
    -0.62
    richTextPanel
    -0.60
    ]--;
    -0.57
    WebElementEntity
    -0.57
    <eos>
    -0.56
    POSITIVE LOGITS
    RectangleBorder
    0.60
    enumii
    0.56
    dată
    0.54
    resizingMask
    0.54
    ịa
    0.54
    BlockPos
    0.53
     Tiro
    0.52
    šanās
    0.52
    giveness
    0.52
    GEBURTS
    0.51
    Activations Density 0.001%

    No Known Activations