© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 76771
    Prev
    Next
    INDEX
    Explanations

    Y

    np_max-act-logits · 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
    abstractmethod
    -0.46
    ttemberg
    -0.44
    (&$
    -0.44
    LocationManager
    -0.43
    ik
    -0.42
    tute
    -0.42
    たまた
    -0.42
    atella
    -0.41
    uffe
    -0.41
    cencia
    -0.40
    POSITIVE LOGITS
     متعلقه
    0.81
    aarrggbb
    0.78
    esterday
    0.68
     виправивши
    0.64
    Демографія
    0.61
     بيها
    0.60
     ddelweddau
    0.59
     للاسماء
    0.59
    AddTagHelper
    0.59
    ESTER
    0.58
    Activations Density 0.004%

    No Known Activations