© 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. 117929
    Prev
    Next
    INDEX
    Explanations

    mutual competition

    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
     المبلغ
    -0.06
     placeholders
    -0.06
    cuna
    -0.06
     pattes
    -0.06
     использование
    -0.06
    これらの
    -0.06
    getic
    -0.06
    मला
    -0.06
     مثلا
    -0.06
     जबकि
    -0.06
    POSITIVE LOGITS
     서로
    0.07
     nhau
    0.07
     mutually
    0.07
     birbir
    0.07
    mutual
    0.06
     afraid
    0.06
    彼此
    0.06
    各自
    0.06
     mutual
    0.06
     soweit
    0.06
    Activations Density 0.035%

    No Known Activations