© 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. 93778
    Prev
    Next
    INDEX
    Explanations

    for

    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
     réguli
    -0.78
     näytte
    -0.62
    YourGuide
    -0.56
     ouvertes
    -0.55
    脚注の使い方
    -0.55
    udah
    -0.55
     automatiques
    -0.53
     Nacionales
    -0.53
    feitura
    -0.52
     régulière
    -0.52
    POSITIVE LOGITS
     חיצוניים
    0.66
    
    0.59
     reasons
    0.59
     kasarigan
    0.58
    CloseOperation
    0.57
    հ
    0.55
     שוליים
    0.54
     Normdatei
    0.53
    VIAF
    0.47
    ürzt
    0.47
    Activations Density 0.002%

    No Known Activations