© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-RES-MATRYOSHKA-DC
    7. 29659
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "COVID"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Aé
    -0.66
    Rujuakan
    -0.65
    TableHead
    -0.65
    Geplaatst
    -0.64
    Vea
    -0.64
     resourceCulture
    -0.63
    PropertyChanging
    -0.63
    tagHelperRunner
    -0.61
    LoadScene
    -0.61
     claws
    -0.60
    POSITIVE LOGITS
     COVID
    1.02
    COVID
    0.92
     Covid
    0.79
    covid
    0.73
    Hentet
    0.72
     covid
    0.70
    UVWXYZ
    0.69
    Covid
    0.68
    vitational
    0.66
    nalités
    0.66
    Activations Density 0.001%

    No Known Activations