© 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. 117557
    Prev
    Next
    INDEX
    Explanations

    negative outcomes or conditions

    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
     reserves
    -0.07
     unspo
    -0.06
    伸び
    -0.06
     Joy
    -0.06
     정상
    -0.06
     Satisfaction
    -0.06
     pursuit
    -0.06
     contentment
    -0.06
    Joy
    -0.06
     normals
    -0.06
    POSITIVE LOGITS
     घातक
    0.07
     peor
    0.07
     miserably
    0.07
     miserable
    0.06
     horribly
    0.06
    ++++++++
    0.06
     notorious
    0.06
     darkly
    0.06
     tragic
    0.06
    etchup
    0.06
    Activations Density 0.048%

    No Known Activations