© 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. 129690
    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
    认为
    -0.06
    認為
    -0.06
     вважа
    -0.06
     Directories
    -0.06
    emptyDict
    -0.06
    baptism
    -0.06
     কাগজ
    -0.06
     invariants
    -0.05
    Editors
    -0.05
    周年
    -0.05
    POSITIVE LOGITS
    :
    0.06
     każdej
    0.06
     -
    0.06
     உட்பட
    0.06
     の
    0.06
    Dis
    0.06
    ses
    0.06
    を含
    0.06
     داخل
    0.06
    distribution
    0.06
    Activations Density 0.000%

    No Known Activations