© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116840
    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
     contacting
    -0.06
    ail
    -0.05
    tan
    -0.05
    
    -0.05
    อื่นๆ
    -0.05
    .:
    -0.05
    HAN
    -0.05
    決め
    -0.05
     مانند
    -0.05
    LM
    -0.05
    POSITIVE LOGITS
     hetzelfde
    0.07
     skirts
    0.06
     logically
    0.06
     QPushButton
    0.06
     ugyan
    0.06
     votre
    0.06
     wiederum
    0.06
    converting
    0.06
    conversion
    0.06
     تلف
    0.06
    Activations Density 0.000%

    No Known Activations