© 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. 119656
    Prev
    Next
    INDEX
    Explanations

    lisk, electrum, Parity, trezor, rotkehlchen, POSW

    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
    propagation
    -0.06
    distribution
    -0.06
     CEO
    -0.06
    💸
    -0.05
    是你
    -0.05
    🔨
    -0.05
     एल्
    -0.05
    raises
    -0.05
     Business
    -0.05
    ont
    -0.05
    POSITIVE LOGITS
     snapshot
    0.07
     erstmal
    0.07
     информация
    0.06
    对应的
    0.06
     وضعیت
    0.06
    専用
    0.06
     informacje
    0.06
     cached
    0.06
     careful
    0.06
     информации
    0.06
    Activations Density 0.005%

    No Known Activations