© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 130731
    Prev
    Next
    INDEX
    Explanations

    investment and investors

    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
     bohemian
    -0.07
     herhangi
    -0.06
     owes
    -0.06
    犹豫
    -0.06
     tämän
    -0.06
    。「
    -0.06
     потра
    -0.06
     humble
    -0.06
     shimmering
    -0.06
     উদার
    -0.06
    POSITIVE LOGITS
     longueur
    0.06
    iento
    0.06
     its
    0.06
     invester
    0.06
    ལ
    0.06
    anzitutto
    0.06
    length
    0.06
     INVEST
    0.06
     our
    0.06
    invest
    0.06
    Activations Density 0.008%

    No Known Activations