© 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. 0-CLT-HP
    7. 97418
    Prev
    Next
    INDEX
    Explanations

    medical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    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
     transfected
    -0.57
    :✨
    -0.55
     Insee
    -0.54
     BrowserModule
    -0.53
     viewDidLoad
    -0.52
     transfection
    -0.51
    roek
    -0.51
     Transplantation
    -0.51
     nervioso
    -0.51
    WebServlet
    -0.50
    POSITIVE LOGITS
    <bos>
    1.32
    AddTagHelper
    0.65
     disambiguazione
    0.61
    ."],
    0.59
    ]");
    0.59
    ]")
    0.59
    Gweler
    0.57
     propOrder
    0.57
    paedia
    0.57
    "):
    0.57
    Activations Density 0.038%

    No Known Activations