© 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. 20-CLT-HP
    7. 72500
    Prev
    Next
    INDEX
    Explanations

    ul

    np_max-act-logits · 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
    AndEndTag
    -0.68
    Parcelize
    -0.56
     الاطلاع
    -0.54
     viewDidLoad
    -0.54
    ArgumentParser
    -0.51
    viewWillAppear
    -0.50
     contextLoads
    -0.48
    essore
    -0.47
     Tenure
    -0.47
     RoutedEventArgs
    -0.46
    POSITIVE LOGITS
    RIQUE
    0.54
     nahilalakip
    0.52
    ⓧ
    0.51
    enderror
    0.50
    igshid
    0.47
    loops
    0.47
    ITTLE
    0.47
    κτή
    0.47
     AssemblyTitle
    0.47
     nakalista
    0.46
    Activations Density 0.005%

    No Known Activations