© 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. 4297
    Prev
    Next
    INDEX
    Explanations

    UITableView

    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
    endus
    -0.75
    MLLoader
    -0.75
    出版年
    -0.66
     hogs
    -0.62
    URERS
    -0.59
    PreferredItem
    -0.58
    FloatField
    -0.58
     Revel
    -0.58
     ttk
    -0.57
    AFX
    -0.56
    POSITIVE LOGITS
    ValueStyle
    0.64
    webElementXpaths
    0.56
     bakgrund
    0.52
     écout
    0.44
     debout
    0.44
     varandra
    0.44
     ***!
    0.43
     vux
    0.43
     ExecuteAsync
    0.43
     automatiques
    0.43
    Activations Density 0.001%

    No Known Activations