© 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. 3264
    Prev
    Next
    INDEX
    Explanations

    programming/technical language

    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
    OGND
    -0.81
    ContentAsync
    -0.62
     tartalomajánló
    -0.61
    DoubleQuotes
    -0.60
     Meksiku
    -0.60
    +#+#
    -0.59
    expandindo
    -0.59
     Rosal
    -0.57
     marrying
    -0.57
    PRNewswire
    -0.57
    POSITIVE LOGITS
     EconPapers
    0.51
    simile
    0.47
    textAppearance
    0.47
     man
    0.45
     CreateTagHelper
    0.44
    FACTS
    0.44
    şme
    0.44
     interés
    0.44
    zugehen
    0.44
    formes
    0.42
    Activations Density 0.000%

    No Known Activations