© 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. 131038
    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
     područ
    -0.07
     dall
    -0.07
     DOE
    -0.06
     affirmat
    -0.06
     Pre
    -0.06
     dichotom
    -0.06
     reputed
    -0.06
    DOE
    -0.06
    ╲
    -0.06
    deselect
    -0.06
    POSITIVE LOGITS
     ఉంది
    0.06
     varias
    0.06
     ય
    0.06
    共享
    0.06
     });
    0.06
     đảm
    0.06
     ہندوستان
    0.06
     Veranstaltung
    0.06
     दर्शा
    0.05
     Bombay
    0.05
    Activations Density 0.000%

    No Known Activations