© 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. 25047
    Prev
    Next
    INDEX
    Explanations

    specific scientific terminology or symbols common in research papers

    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
    errHandler
    -0.60
    javas
    -0.49
    ogie
    -0.48
     fto
    -0.48
    andExpect
    -0.47
    Xna
    -0.46
    ueba
    -0.46
    IFO
    -0.45
     Solidity
    -0.45
     Os
    -0.45
    POSITIVE LOGITS
    rrggbb
    0.76
     виправивши
    0.73
     disambiguazione
    0.72
     وتسجيلات
    0.64
     nahilalakip
    0.64
    VersionUID
    0.63
     ویکی‌پدیای
    0.60
    SourceChecksum
    0.59
     resourceCulture
    0.59
    yntaxException
    0.59
    Activations Density 0.040%

    No Known Activations