© 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. 119459
    Prev
    Next
    INDEX
    Explanations

    encryption, public key, decryption

    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
    每个
    -0.07
     기준
    -0.06
     Appalach
    -0.06
    each
    -0.06
     at
    -0.06
    ব্যা
    -0.06
     in
    -0.06
     sechs
    -0.06
     부족
    -0.06
    ливо
    -0.06
    POSITIVE LOGITS
     使用
    0.07
    Converter
    0.06
     convert
    0.06
    自分で
    0.06
     leveraging
    0.06
     mutual
    0.06
     সিংহের
    0.06
    信心
    0.06
     お
    0.06
     emailed
    0.06
    Activations Density 0.010%

    No Known Activations