© 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. 118186
    Prev
    Next
    INDEX
    Explanations

    catch block, finally block

    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
     hızlı
    -0.07
    model
    -0.07
    快速
    -0.07
    早速
    -0.06
     nhanh
    -0.06
     schneller
    -0.06
     könny
    -0.06
    inese
    -0.06
    𝓜
    -0.06
     quicker
    -0.06
    POSITIVE LOGITS
     security
    0.06
     scavenging
    0.06
     versión
    0.06
     certainly
    0.06
     protective
    0.06
     பாதுகாப்பு
    0.06
     coexistence
    0.06
     supplemental
    0.06
     sør
    0.06
    oxet
    0.06
    Activations Density 0.002%

    No Known Activations