© 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. 130117
    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
     ۸
    -0.07
     ۶
    -0.06
     incredibly
    -0.06
     매우
    -0.06
     experimenting
    -0.06
     enorm
    -0.06
     অনেক
    -0.06
     EZ
    -0.06
     помо
    -0.06
     clue
    -0.06
    POSITIVE LOGITS
    或
    0.07
     अथवा
    0.07
    或其他
    0.07
     किंवा
    0.06
     அல்லது
    0.06
     या
    0.06
    或者
    0.06
    または
    0.06
     ወይም
    0.06
     또는
    0.06
    Activations Density 0.000%

    No Known Activations