© 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. 1-CLT-HP
    7. 11713
    Prev
    Next
    INDEX
    Explanations

    refreshing or relapsing

    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
     relapse
    -1.19
    apse
    -0.87
    lapsed
    -0.78
    lapse
    -0.69
    NUMX
    -0.59
     lapse
    -0.58
     lapsed
    -0.58
    pses
    -0.56
    coledì
    -0.56
    parseLong
    -0.54
    POSITIVE LOGITS
    routeProvider
    0.62
     تضيفلها
    0.61
     indietro
    0.59
     estekak
    0.59
     viewDidLoad
    0.57
     CGSize
    0.54
     חיצוניים
    0.54
    Geplaatst
    0.54
     विश्वसनीयता
    0.52
    
    0.51
    Activations Density 0.102%

    No Known Activations