© 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. 10688
    Prev
    Next
    INDEX
    Explanations

    patterns and structures in mathematical notation, particularly related to integrals and functions

    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
    ]--;
    -0.60
    참고
    -0.56
     ejected
    -0.52
    PerformLayout
    -0.51
     historians
    -0.50
     endDate
    -0.50
     Sohn
    -0.49
     agrico
    -0.49
    DataSnapshot
    -0.49
     Gentiles
    -0.49
    POSITIVE LOGITS
    tagHelperRunner
    0.90
    Rüyada
    0.79
     AssemblyCulture
    0.71
     pinulongan
    0.66
     AssemblyTitle
    0.66
    SharedDtor
    0.64
     StringTokenizer
    0.63
     EconPapers
    0.60
    glGen
    0.59
    ViewImports
    0.59
    Activations Density 0.074%

    No Known Activations