© 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. 116928
    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
    starting
    -0.07
     starting
    -0.07
     Starting
    -0.06
     звер
    -0.06
    Starting
    -0.06
    abes
    -0.06
    বান্ধ
    -0.06
     immerse
    -0.05
    hhhhhhhh
    -0.05
    <strong>
    -0.05
    POSITIVE LOGITS
     পেনশন
    0.07
     cláss
    0.07
     дает
    0.06
    frank
    0.06
     трево
    0.06
    ឬ
    0.06
     relacionada
    0.06
     velocity
    0.06
    дает
    0.06
     слоя
    0.06
    Activations Density 0.000%

    No Known Activations