© 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. 94936
    Prev
    Next
    INDEX
    Explanations

    of

    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
    iform
    -0.53
    combe
    -0.52
    Post
    -0.49
    årige
    -0.49
    országban
    -0.48
     mijne
    -0.47
    ulite
    -0.47
    Pane
    -0.47
    DidChange
    -0.47
    posts
    -0.46
    POSITIVE LOGITS
     مشين
    0.96
     between
    0.77
     Roskov
    0.72
    MigrationBuilder
    0.61
    AddTagHelper
    0.58
     '\\;'
    0.56
    CloseOperation
    0.56
     Between
    0.54
    ValueStyle
    0.54
     RoutedEventArgs
    0.53
    Activations Density 0.001%

    No Known Activations