© 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. 3662
    Prev
    Next
    INDEX
    Explanations

    as

    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
    hence
    -0.44
     wir
    -0.42
    either
    -0.41
    ')['
    -0.40
     lac
    -0.40
    つまり
    -0.40
    ```
    -0.40
    rowa
    -0.39
    PREFIX
    -0.38
     AUSSI
    -0.38
    POSITIVE LOGITS
    GEBURTSDATUM
    0.81
     calendriers
    0.69
     الرخصة
    0.69
     kasarigan
    0.69
     Roskov
    0.68
     CreateTagHelper
    0.67
    termilk
    0.66
     AssemblyCulture
    0.66
    Autoritní
    0.66
    TintMode
    0.66
    Activations Density 0.000%

    No Known Activations