© 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. 118939
    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
    特殊
    -0.07
    拽
    -0.06
     lokasi
    -0.06
     streamers
    -0.06
     recordando
    -0.06
     recordar
    -0.06
     locations
    -0.06
     специальных
    -0.06
     Aula
    -0.05
    hund
    -0.05
    POSITIVE LOGITS
     use
    0.06
    safe
    0.06
     understanding
    0.06
    我們
    0.06
     pract
    0.06
    我们在
    0.06
    想法
    0.06
     сути
    0.06
     중요한
    0.06
     useful
    0.06
    Activations Density 0.002%

    No Known Activations