© 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. 129151
    Prev
    Next
    INDEX
    Explanations

    communication and contact

    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
     membership
    -0.06
     disenfranch
    -0.06
     none
    -0.06
    強制
    -0.06
    强制
    -0.06
     constraint
    -0.06
     maze
    -0.06
    褔
    -0.06
    편
    -0.06
     anomalies
    -0.06
    POSITIVE LOGITS
     contact
    0.08
    連絡
    0.08
     контак
    0.06
    沟通
    0.06
    leftrightarrow
    0.06
     keep
    0.06
     kommun
    0.06
     CONTACT
    0.06
     communication
    0.06
     communicate
    0.06
    Activations Density 0.001%

    No Known Activations