© 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. 118536
    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
     one
    -0.08
     ব্যক্তিদের
    -0.06
     또한
    -0.06
     ११
    -0.06
    لیل
    -0.06
     lại
    -0.06
    이상
    -0.06
    🔐
    -0.06
    또한
    -0.06
     spies
    -0.06
    POSITIVE LOGITS
     unsafe
    0.06
    Trong
    0.05
     조사
    0.05
     тексто
    0.05
     huống
    0.05
     ক্রি
    0.05
    ীশ
    0.05
     unstable
    0.05
     unser
    0.05
     heartbeat
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.