© 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. 130028
    Prev
    Next
    INDEX
    Explanations

    business and finance terms

    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
     mediante
    -0.06
     alguno
    -0.06
     focused
    -0.06
    monday
    -0.06
     vib
    -0.06
     princ
    -0.06
     Breaking
    -0.06
     Princes
    -0.06
    സര്‍
    -0.06
     uncommon
    -0.06
    POSITIVE LOGITS
     sources
    0.07
     source
    0.07
     validity
    0.07
     Sources
    0.06
     lógica
    0.06
     źród
    0.06
     किस्म
    0.06
    enth
    0.06
    起
    0.06
    生活
    0.06
    Activations Density 0.024%

    No Known Activations