© 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. 128484
    Prev
    Next
    INDEX
    Explanations

    negative events or situations

    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
     intitulé
    -0.07
     πρώ
    -0.06
    projectName
    -0.06
    含
    -0.06
     rencontre
    -0.06
     berjudul
    -0.06
     teammate
    -0.06
     impactful
    -0.05
     novità
    -0.05
     первый
    -0.05
    POSITIVE LOGITS
     सभी
    0.08
    這些
    0.08
     جميع
    0.08
    每
    0.07
     για
    0.07
     برای
    0.07
     всички
    0.07
     всіх
    0.07
     pentru
    0.07
    沒有
    0.07
    Activations Density 0.017%

    No Known Activations