© 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. 118446
    Prev
    Next
    INDEX
    Explanations

    financial success and ruin

    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
     Treaty
    -0.06
    费用
    -0.06
     biaya
    -0.06
    ༼
    -0.06
     erforder
    -0.06
    费
    -0.06
     notables
    -0.06
     elevado
    -0.06
    ರಿಯ
    -0.06
    Annual
    -0.06
    POSITIVE LOGITS
     سایر
    0.06
     pristine
    0.06
     versatile
    0.06
     unter
    0.05
     frequ
    0.05
     partially
    0.05
     precisely
    0.05
                      
    0.05
     سطح
    0.05
     newly
    0.05
    Activations Density 0.009%

    No Known Activations