© 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. 4-CLT-HP
    7. 1203
    Prev
    Next
    INDEX
    Explanations

    URLs, HTTP, web requests

    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
     debris
    -0.47
     stubble
    -0.46
     fertil
    -0.45
     freckles
    -0.45
     soaps
    -0.44
     miscellaneous
    -0.43
    سيم
    -0.43
     curfew
    -0.43
     quadrilateral
    -0.43
    ant
    -0.43
    POSITIVE LOGITS
    ://
    0.90
    UrlResolution
    0.90
    URLException
    0.83
    bootstrapcdn
    0.79
    WebVitals
    0.71
    WriteTagHelper
    0.67
    IsContent
    0.66
     defaultstate
    0.66
    ècie
    0.65
     Normdatei
    0.63
    Activations Density 0.233%

    No Known Activations