© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118482
    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
     equivalents
    -0.07
    唱歌
    -0.07
    踽
    -0.06
     überhaupt
    -0.06
     علماء
    -0.06
     acronym
    -0.06
     SCHOOL
    -0.06
     RBI
    -0.06
    탯
    -0.06
    少なくとも
    -0.06
    POSITIVE LOGITS
     художе
    0.07
     নিয়ন্ত্রণ
    0.06
     kült
    0.06
     безопасность
    0.06
    文化的
    0.06
     prince
    0.06
     männer
    0.06
    wesen
    0.06
     ایران
    0.06
     опасность
    0.06
    Activations Density 0.000%

    No Known Activations