© 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. 118967
    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
     eclectic
    -0.07
     ಯಾವಾಗ
    -0.06
     surrounds
    -0.06
     surround
    -0.06
     enkele
    -0.06
     falsehood
    -0.06
     encir
    -0.06
    குடும்ப
    -0.06
    cerning
    -0.06
     fortn
    -0.06
    POSITIVE LOGITS
     muốn
    0.06
    这
    0.06
     για
    0.06
     就
    0.06
     Complaints
    0.06
    就
    0.06
    需要
    0.06
    DB
    0.06
     registered
    0.06
     குறிப்பிட்ட
    0.05
    Activations Density 0.000%

    No Known Activations