© 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
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 29500
    Prev
    Next
    INDEX
    Explanations

    mentions of grades in medical contexts, especially grades 3 and 4, and classes 2 and 4

    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
     coordonnées
    -0.57
    farin
    -0.55
    Bly
    -0.54
    oxone
    -0.52
    DeleteCommand
    -0.52
    dasarkan
    -0.52
     numé
    -0.52
     Wiktionnaire
    -0.52
    anair
    -0.51
    labus
    -0.51
    POSITIVE LOGITS
    Tertiary
    0.73
     crdi
    0.71
     tertiary
    0.69
     Tertiary
    0.69
     tfsi
    0.66
    SourceChecksum
    0.66
    istoitu
    0.65
    BagLayout
    0.62
     Shakti
    0.62
     Uru
    0.61
    Activations Density 0.033%

    No Known Activations