© 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. 5-CLT-HP
    7. 94883
    Prev
    Next
    INDEX
    Explanations

    companies and organizations

    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
     estekak
    -0.64
    例文帳に追加
    -0.52
     resourceCulture
    -0.52
     дописавши
    -0.48
     GenerationType
    -0.47
     autorytatywna
    -0.47
    createCanvas
    -0.44
     Paglinawan
    -0.44
    ########.
    -0.40
     bucal
    -0.40
    POSITIVE LOGITS
    UIImageView
    0.59
    openConnection
    0.57
    ClientRect
    0.56
    eriksaan
    0.56
    tabBar
    0.55
    DateTimeField
    0.55
    theoremstyle
    0.55
     ​​
    0.55
     getPassword
    0.54
     PackageManager
    0.54
    Activations Density 0.014%

    No Known Activations