© 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. 116293
    Prev
    Next
    INDEX
    Explanations

    java activity `onCreate`

    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
    ᕝ
    -0.07
     cuisses
    -0.07
    一段
    -0.06
     puissance
    -0.06
     যুদ্ধে
    -0.06
    uteurs
    -0.06
    tipo
    -0.06
     getCurrent
    -0.06
    nuevo
    -0.06
    ogados
    -0.06
    POSITIVE LOGITS
    प्रा
    0.06
    प्रत्य
    0.06
     ().
    0.06
    MetaData
    0.06
    ್ರ
    0.06
    Alright
    0.06
    ड
    0.06
    स्वरूप
    0.05
     masc
    0.05
     čast
    0.05
    Activations Density 0.001%

    No Known Activations