© 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. 0-CLT-HP
    7. 41884
    Prev
    Next
    INDEX
    Explanations

    Coo

    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
    xo
    -0.45
     кӀош
    -0.42
    switch
    -0.41
    če
    -0.36
     kılı
    -0.36
    Received
    -0.36
    rodow
    -0.35
    xy
    -0.35
     primeiras
    -0.34
     switching
    -0.33
    POSITIVE LOGITS
     BoxDecoration
    0.93
    GraphicsUnit
    0.91
     تضيفلها
    0.83
     kaarangay
    0.80
     محفوظة
    0.79
     препратки
    0.79
    Enllaces
    0.79
    AddTagHelper
    0.77
    WaitGroup
    0.77
    HandlerContext
    0.76
    Activations Density 0.284%

    No Known Activations