© 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. 118710
    Prev
    Next
    INDEX
    Explanations

    interlocking, embedded, self-adhering

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    政府
    -0.07
     появление
    -0.06
     Gar
    -0.06
     directives
    -0.06
     apari
    -0.06
     refinements
    -0.06
     அரசா
    -0.06
     arrivals
    -0.06
     появления
    -0.06
     annotations
    -0.06
    POSITIVE LOGITS
     Remain
    0.06
     destek
    0.06
     stayed
    0.06
     barring
    0.06
     ஆத
    0.06
    Tak
    0.06
    ่วง
    0.06
    perman
    0.06
    Mixing
    0.06
     поддержи
    0.06
    Activations Density 0.025%

    No Known Activations