© 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. 12425
    Prev
    Next
    INDEX
    Explanations

    quotation marks and commas

    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
    ttu
    -0.47
    BagLayout
    -0.47
    scalatest
    -0.46
    TagHelper
    -0.44
    TagMode
    -0.43
    stylers
    -0.43
    
    -0.43
    createForm
    -0.42
     ๆ
    -0.41
    श्चित
    -0.41
    POSITIVE LOGITS
    Referències
    0.56
     vastaan
    0.55
     Tert
    0.53
    putan
    0.53
     Masih
    0.52
     Peker
    0.52
     Mubarak
    0.52
     Anas
    0.51
     raiſ
    0.51
    ksesta
    0.50
    Activations Density 0.009%

    No Known Activations