© 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. 5-CLT-HP
    7. 4268
    Prev
    Next
    INDEX
    Explanations

    licenses

    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
    AddHtmlAttribute
    -0.55
    SETTINGS
    -0.54
    WriteLiteral
    -0.53
     CreateTagHelper
    -0.53
    scrapy
    -0.51
    Edited
    -0.51
     prédé
    -0.50
    Achievements
    -0.50
    addComponent
    -0.49
     Campaign
    -0.49
    POSITIVE LOGITS
    новништво
    0.56
     دیکھیے
    0.47
     otomatig
    0.47
    rungsseite
    0.47
    ::__
    0.45
    Buildable
    0.44
     esternos
    0.44
    atrician
    0.43
    ware
    0.41
    Entonces
    0.41
    Activations Density 0.437%

    No Known Activations