© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 115988
    Prev
    Next
    INDEX
    Explanations

    tracking and maintaining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     výsled
    -0.07
    ürlich
    -0.06
    碁
    -0.06
     eru
    -0.06
    トレーニング
    -0.06
     сокра
    -0.06
     których
    -0.06
    PointCloud
    -0.06
     electrification
    -0.06
     از
    -0.06
    POSITIVE LOGITS
     mantener
    0.07
    维持
    0.07
     sustaining
    0.07
     initiale
    0.07
     maintaining
    0.06
     अनुया
    0.06
    跟踪
    0.06
    เคลื่อน
    0.06
     while
    0.06
     suivre
    0.06
    Activations Density 0.001%

    No Known Activations