© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119390
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    みたいな
    -0.07
     probably
    -0.06
     personalities
    -0.06
     hasonló
    -0.06
     लोकप्रिय
    -0.06
     ordinateur
    -0.06
    listeners
    -0.05
    Wür
    -0.05
     аўтаматы
    -0.05
     cellpadding
    -0.05
    POSITIVE LOGITS
    进一步
    0.06
     قیامت
    0.06
     最新
    0.06
    lene
    0.06
    sene
    0.06
    Minimal
    0.06
     সবসময়
    0.06
    postgresql
    0.06
    បន្ថ
    0.06
     Minimal
    0.06
    Activations Density 0.000%

    No Known Activations