© 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. 117236
    Prev
    Next
    INDEX
    Explanations

    association

    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
     کمک
    -0.07
     simplicity
    -0.06
     MAN
    -0.06
    helper
    -0.06
     optimizing
    -0.06
     aides
    -0.06
     हादसे
    -0.06
     SOL
    -0.06
     strategies
    -0.06
    Many
    -0.06
    POSITIVE LOGITS
     associated
    0.08
     asociado
    0.07
     здесь
    0.07
     соответствующих
    0.07
    associated
    0.06
     associé
    0.06
     معه
    0.06
     в
    0.06
     обычно
    0.06
     ассо
    0.06
    Activations Density 0.003%

    No Known Activations