© 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. 130007
    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
    AIDS
    -0.07
     documented
    -0.06
    quest
    -0.06
     różnych
    -0.05
     engineered
    -0.05
     solub
    -0.05
     AIDS
    -0.05
     entre
    -0.05
    各类
    -0.05
     Consultancy
    -0.05
    POSITIVE LOGITS
    riffe
    0.07
     perfectly
    0.06
    ৪৯
    0.06
     châu
    0.06
    quite
    0.06
     εκεί
    0.06
    స్తాయి
    0.06
    দির
    0.06
     રાખી
    0.06
     관심을
    0.06
    Activations Density 0.000%

    No Known Activations