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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 131020
    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
    修为
    -0.06
     চিকিৎসা
    -0.06
     amount
    -0.06
     expanded
    -0.06
     size
    -0.06
    每个人
    -0.06
     расстояние
    -0.06
     miejsca
    -0.06
     prendre
    -0.05
     cumplir
    -0.05
    POSITIVE LOGITS
     often
    0.07
     često
    0.07
     related
    0.06
     často
    0.06
     сравни
    0.06
     sometimes
    0.06
     spesso
    0.06
     বিখ্যাত
    0.06
     metaverse
    0.06
    抽象
    0.06
    Activations Density 0.004%

    No Known Activations