© 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. 0-CLT-HP
    7. 38463
    Prev
    Next
    INDEX
    Explanations

    scientific/technical contexts

    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
    trons
    -0.57
    shire
    -0.54
    はじめに
    -0.53
    Üdv
    -0.52
    nestjs
    -0.51
     forecast
    -0.51
     anomalous
    -0.50
    tintColor
    -0.50
    illai
    -0.50
     GENERATED
    -0.50
    POSITIVE LOGITS
     onCreateView
    0.89
    DockStyle
    0.69
     klara
    0.63
    findpost
    0.58
    
    0.54
    XmlAccessorType
    0.51
    nativeElement
    0.51
    GEBURTSDATUM
    0.50
    WebVitals
    0.50
    utilisons
    0.49
    Activations Density 1.620%

    No Known Activations