© 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. 1-CLT-HP
    7. 13902
    Prev
    Next
    INDEX
    Explanations

    might

    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
    TagMode
    -0.96
    +#+#
    -0.87
     autorytatywna
    -0.80
    الدراسه
    -0.79
     kasarigan
    -0.70
     kaarangay
    -0.69
     مرئيه
    -0.67
    bootstrapcdn
    -0.66
    AddTagHelper
    -0.65
     Chwiliwch
    -0.64
    POSITIVE LOGITS
     рода
    0.41
    unzel
    0.41
     newArray
    0.39
     Masa
    0.39
     joya
    0.38
    下手
    0.38
    جار
    0.38
    씨
    0.38
    boldmath
    0.37
     big
    0.37
    Activations Density 0.002%

    No Known Activations