© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92263
    Prev
    Next
    INDEX
    Explanations

    licensing agreements and furnished items

    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
     فريبيس
    -0.99
    OGND
    -0.97
     resourceCulture
    -0.86
     CreateTagHelper
    -0.84
    UnusedPrivate
    -0.84
     mergeFrom
    -0.78
    contentLoaded
    -0.75
    RegistryLite
    -0.74
    HasAnnotation
    -0.73
     समीक्षाएं
    -0.72
    POSITIVE LOGITS
    Consigli
    0.50
     for
    0.46
     already
    0.46
     määrä
    0.45
     in
    0.45
     Gerais
    0.42
    ,
    0.41
     though
    0.41
     Universal
    0.41
    .
    0.40
    Activations Density 1.239%

    No Known Activations