© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 634
    Prev
    Next
    INDEX
    Explanations

    introducing a topic

    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
     long
    -0.50
     électronique
    -0.49
     longue
    -0.47
     longtemps
    -0.47
     paix
    -0.47
     présidenti
    -0.46
     électroniques
    -0.46
     abandonné
    -0.46
     longues
    -0.46
     förstå
    -0.43
    POSITIVE LOGITS
     &___
    0.85
    Hentet
    0.77
    ///</
    0.73
    BeginInit
    0.71
    SuspendLayout
    0.66
    TagHelper
    0.66
    ContentAsync
    0.66
    المناصب
    0.65
     kasarigan
    0.64
    rdom
    0.63
    Activations Density 0.006%

    No Known Activations