© 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. 119150
    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
    Nome
    -0.06
     harnessed
    -0.06
    indeed
    -0.06
    Facebook
    -0.06
    ľad
    -0.06
    選擇
    -0.06
     unprecedented
    -0.06
     youths
    -0.06
    முற
    -0.06
     Indeed
    -0.06
    POSITIVE LOGITS
     HDMI
    0.07
     gyárt
    0.07
    婚姻
    0.06
    HDMI
    0.06
     продви
    0.06
     পাঠানো
    0.06
     жени
    0.06
     সত্ত্বেও
    0.06
    ಕ್ಕೂ
    0.06
     exporter
    0.06
    Activations Density 0.000%

    No Known Activations