© 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. 1-CLT-HP
    7. 14689
    Prev
    Next
    INDEX
    Explanations

    cities and universities

    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
     '\\;'
    -0.81
    endphp
    -0.71
    GEBURTSDATUM
    -0.70
    AddTagHelper
    -0.70
    脚注の使い方
    -0.69
     فريبيس
    -0.68
     חיצוניים
    -0.68
    RenderAtEndOf
    -0.66
    expandindo
    -0.66
    PerformLayout
    -0.64
    POSITIVE LOGITS
     disease
    0.46
     Disease
    0.43
     mouseClicked
    0.42
    Soft
    0.41
     Funky
    0.41
     leyendo
    0.40
    ungalows
    0.39
    رياض
    0.39
     osteoporosis
    0.38
     Soft
    0.37
    Activations Density 0.011%

    No Known Activations