© 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. 1511
    Prev
    Next
    INDEX
    Explanations

    war texts

    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
    kező
    -0.54
     volna
    -0.47
     veuillez
    -0.46
     képes
    -0.46
     싶
    -0.44
    JsonFormat
    -0.44
     sélectionnez
    -0.43
    싶
    -0.42
    URIComponent
    -0.42
     antaranya
    -0.42
    POSITIVE LOGITS
     дописавши
    0.82
    UnsafeEnabled
    0.82
    webElementXpaths
    0.81
    complexContent
    0.80
    
    0.77
     تضيفلها
    0.75
     propOrder
    0.74
    elemField
    0.71
    GEBURTSDATUM
    0.71
     ostavi
    0.69
    Activations Density 0.033%

    No Known Activations