© 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. 5-CLT-HP
    7. 100
    Prev
    Next
    INDEX
    Explanations

    wine

    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
    yards
    -0.59
    ferrous
    -0.57
     lära
    -0.57
    glades
    -0.56
    alyptus
    -0.56
    σθαι
    -0.56
     Gea
    -0.54
    ündigung
    -0.54
    gica
    -0.54
    جغرافيا
    -0.53
    POSITIVE LOGITS
     CreateTagHelper
    0.48
    nah
    0.47
    mycompany
    0.44
    labelledby
    0.42
    Hentet
    0.41
    sqcup
    0.40
     ExecuteAsync
    0.40
    BrowserModule
    0.39
    enero
    0.39
     dug
    0.39
    Activations Density 0.007%

    No Known Activations