© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 131026
    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
     any
    -0.06
     própri
    -0.06
     those
    -0.05
    ակ
    -0.05
     вдруг
    -0.05
    ธิ
    -0.05
     a
    -0.05
    विण्यासाठी
    -0.05
     Changer
    -0.05
     (
    -0.05
    POSITIVE LOGITS
     Algunas
    0.07
     ohne
    0.07
     sarà
    0.07
     پور
    0.06
     tanpa
    0.06
     crear
    0.06
     spazi
    0.06
     कार्यकारिणी
    0.06
     رہی
    0.06
    ;
    0.06
    Activations Density 0.002%

    No Known Activations