© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93439
    Prev
    Next
    INDEX
    Explanations

    KDE, Gnome, Gtk

    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
    tagHelperRunner
    -0.84
    CopyWith
    -0.68
    HostException
    -0.63
     kasarigan
    -0.62
    ChromeDriver
    -0.60
    laubnis
    -0.56
     octavo
    -0.54
    原始内容存档于
    -0.54
    protoimpl
    -0.54
     mcd
    -0.53
    POSITIVE LOGITS
    $_['
    0.66
    3
    0.62
    Демографія
    0.54
    occasione
    0.53
     Bellamy
    0.52
     Shell
    0.50
    RenderAtEndOf
    0.49
    impresa
    0.48
     Three
    0.46
    three
    0.46
    Activations Density 0.006%

    No Known Activations