© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 115884
    Prev
    Next
    INDEX
    Explanations

    questions about lockdown

    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
    Negative Logits
    ství
    -0.07
     सीधे
    -0.07
     hés
    -0.06
    とりあえず
    -0.06
     kanske
    -0.06
     contenant
    -0.06
    ورہ
    -0.06
     modulating
    -0.06
     கூடுதல்
    -0.06
     possibile
    -0.06
    POSITIVE LOGITS
    what
    0.06
     what
    0.06
     during
    0.06
    these
    0.06
     Lockdown
    0.06
     which
    0.06
    という
    0.06
     라는
    0.06
     lockdown
    0.06
     लॉकडाउन
    0.06
    Activations Density 0.001%

    No Known Activations