© 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. 4-CLT-HP
    7. 2638
    Prev
    Next
    INDEX
    Explanations

    time, schedules

    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
     Paglinawan
    -0.67
    FXMLLoader
    -0.54
    SourceChecksum
    -0.52
    $_['
    -0.51
    AlterField
    -0.49
    ystic
    -0.49
    |}\
    -0.48
    istaa
    -0.48
    WireFormatLite
    -0.47
    '])){
    -0.46
    POSITIVE LOGITS
    Released
    0.58
     tide
    0.54
     saites
    0.52
     released
    0.52
     OnInit
    0.50
     violation
    0.49
    enação
    0.48
     submission
    0.48
    Билгалдахарш
    0.48
     appointment
    0.48
    Activations Density 0.010%

    No Known Activations