© 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. 5-CLT-HP
    7. 5353
    Prev
    Next
    INDEX
    Explanations

    many

    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
     rest
    -0.57
     Rest
    -0.47
     Rood
    -0.41
    licante
    -0.41
     cotton
    -0.41
    Rest
    -0.40
     REST
    -0.40
     sessionFactory
    -0.39
     Previous
    -0.39
    nextDouble
    -0.39
    POSITIVE LOGITS
    ArrowToggle
    0.81
     such
    0.81
    UnsafeEnabled
    0.75
    Dữ
    0.71
    InSection
    0.69
     שוליים
    0.69
    such
    0.68
     SUCH
    0.67
     CreateTagHelper
    0.67
    TagMode
    0.66
    Activations Density 0.002%

    No Known Activations