© 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. 129482
    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
     ini
    -0.06
     podcast
    -0.06
     inp
    -0.06
     deliberate
    -0.06
     thanking
    -0.06
     sketches
    -0.06
    Congratulations
    -0.06
     congrat
    -0.05
     likely
    -0.05
     sketching
    -0.05
    POSITIVE LOGITS
     cardiomyocytes
    0.06
     //[
    0.06
     Diện
    0.06
     μετά
    0.06
     खड़े
    0.06
    ﺸ
    0.06
    ᄉ
    0.06
     собствен
    0.06
     হয়নি
    0.06
     mengembangkan
    0.06
    Activations Density 0.000%

    No Known Activations