© 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. 119050
    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
     antara
    -0.07
    原则
    -0.06
    ضور
    -0.06
     scarce
    -0.06
     প্রায়
    -0.06
    입
    -0.06
     ভালোবাস
    -0.06
     những
    -0.06
     എന്നിവ
    -0.06
     zerstört
    -0.06
    POSITIVE LOGITS
     கூட
    0.06
    腎
    0.06
     instruct
    0.06
    Param
    0.05
    就像
    0.05
     जस्ट
    0.05
     evocative
    0.05
     paramet
    0.05
    imple
    0.05
     genauso
    0.05
    Activations Density 0.000%

    No Known Activations