© 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. 118376
    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
    相应的
    -0.08
    相应
    -0.08
     seemingly
    -0.06
    沒有
    -0.06
     accumulated
    -0.06
    相對
    -0.06
     entsprechend
    -0.06
     Krankenhaus
    -0.06
     соответственно
    -0.06
     keine
    -0.06
    POSITIVE LOGITS
    வரின்
    0.06
     Pasal
    0.06
    ieurs
    0.06
     اگ
    0.06
    波
    0.05
     प्रेरक
    0.05
     IM
    0.05
     artyku
    0.05
     partnership
    0.05
    ডির
    0.05
    Activations Density 0.000%

    No Known Activations