© 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. 0-RES-MATRYOSHKA-DC
    7. 10535
    Prev
    Next
    INDEX
    Explanations

    references to the importance or significance of a subject

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    varande
    -0.60
    licitations
    -0.60
    DoubleQuotes
    -0.59
    ciful
    -0.58
    boh
    -0.58
     Inputs
    -0.57
     Ditto
    -0.57
    Искәрмәләр
    -0.56
    Часть
    -0.56
    helves
    -0.56
    POSITIVE LOGITS
     trebui
    0.64
    enance
    0.62
     should
    0.61
     preferably
    0.61
    脚注の使い方
    0.58
    tagext
    0.58
    preferably
    0.56
    lepiej
    0.56
     powinna
    0.56
     хотелось
    0.54
    Activations Density 0.050%

    No Known Activations