© 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. 0-CLT-HP
    7. 40718
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
     appliance
    -0.72
     Myers
    -0.71
    __(/*!
    -0.65
    دانشنامهٔ
    -0.65
     оригіналу
    -0.61
    -------------</
    -0.61
     possession
    -0.59
    GHIJKLM
    -0.59
    İstinadlar
    -0.59
     سكانية
    -0.59
    POSITIVE LOGITS
    RegressionTest
    0.65
     بتاريخ
    0.50
     raggiunto
    0.50
     puse
    0.47
    ry
    0.43
     Teut
    0.43
     Sout
    0.43
    гей
    0.42
     Saty
    0.42
     voglio
    0.41
    Activations Density 0.198%

    No Known Activations