© 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. 43904
    Prev
    Next
    INDEX
    Explanations

    code/programming

    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
     Procure
    -0.65
     AssemblyCulture
    -0.64
     scraping
    -0.64
    httphttps
    -0.63
    s
    -0.60
    sing
    -0.60
     procure
    -0.60
    Pratique
    -0.57
     procuring
    -0.56
    NavController
    -0.55
    POSITIVE LOGITS
    ')")
    0.61
     veta
    0.60
    UAWEI
    0.60
    Personendaten
    0.59
    يار
    0.56
    imation
    0.56
     igång
    0.55
    ')));
    0.55
    RegressionTest
    0.55
    دانشنامهٔ
    0.54
    Activations Density 0.924%

    No Known Activations