© 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. 92630
    Prev
    Next
    INDEX
    Explanations

    Technical/academic source

    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
     Drapeau
    -0.54
     BitmapFactory
    -0.51
    RunAsync
    -0.49
    PageFactory
    -0.49
    ectady
    -0.49
     vinci
    -0.49
     CreateTagHelper
    -0.48
    RequestOptions
    -0.47
    OGND
    -0.47
     Zeppelin
    -0.46
    POSITIVE LOGITS
     chré
    0.65
     Abor
    0.57
     članak
    0.55
     supérieurs
    0.54
     suivez
    0.53
     nôtre
    0.53
    ViewFeatures
    0.52
     européens
    0.52
    bootstrapcdn
    0.51
     direta
    0.51
    Activations Density 0.027%

    No Known Activations