© 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. 1-CLT-HP
    7. 781
    Prev
    Next
    INDEX
    Explanations

    Southern

    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
     AssemblyCulture
    -0.79
     disambiguazione
    -0.79
    afficheront
    -0.71
    例文帳に追加
    -0.69
    zeitige
    -0.68
    Jeografia
    -0.68
    Bibliograf
    -0.68
     Wiktionnaire
    -0.68
     Undeclared
    -0.67
    IUrlHelper
    -0.66
    POSITIVE LOGITS
    Col
    0.48
    ↪
    0.45
     Col
    0.44
     doGet
    0.44
     find
    0.44
    weichen
    0.43
     col
    0.41
    badlogic
    0.40
    FromArgb
    0.40
    iencing
    0.40
    Activations Density 0.005%

    No Known Activations