© 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. 2839
    Prev
    Next
    INDEX
    Explanations

    blog comments

    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
     bande
    -0.54
     كمان
    -0.47
    #
    -0.47
    بوابة
    -0.45
    Thank
    -0.45
     lietu
    -0.44
     maschile
    -0.43
     AssemblyTitle
    -0.42
    m
    -0.42
     curd
    -0.42
    POSITIVE LOGITS
     CreateTagHelper
    0.73
    verifyException
    0.70
    phazard
    0.62
    Personensuche
    0.59
    ngthen
    0.59
    UnusedPrivate
    0.59
    სქოლიო
    0.59
     Мексичка
    0.58
    @[+][
    0.57
    setVerticalGroup
    0.57
    Activations Density 0.053%

    No Known Activations