© 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. 118104
    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
     multilingual
    -0.06
     cenu
    -0.06
     image
    -0.05
     потря
    -0.05
     estampado
    -0.05
     শহ
    -0.05
    获奖
    -0.05
    筒
    -0.05
     такими
    -0.05
    ائرة
    -0.05
    POSITIVE LOGITS
     регулярно
    0.08
    定期
    0.08
     quickly
    0.08
     weekly
    0.07
     PROFESSION
    0.07
    每周
    0.07
    quickly
    0.07
     regularly
    0.07
    okane
    0.07
    📋
    0.07
    Activations Density 0.000%

    No Known Activations