© 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. 97237
    Prev
    Next
    INDEX
    Explanations

    imitation and invasion

    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
    tonsoft
    -0.86
    
    -0.82
    ьаж
    -0.71
    EndGlobalSection
    -0.69
    WriteBarrier
    -0.68
     ویکی‌پدیا
    -0.68
    addCriterion
    -0.68
     незавершена
    -0.68
    ItemBackground
    -0.66
     Савезне
    -0.65
    POSITIVE LOGITS
     Elabor
    0.49
    ency
    0.48
    ous
    0.48
    Enumerable
    0.47
    cy
    0.47
    zame
    0.47
    ge
    0.46
    anged
    0.46
    ger
    0.45
     Vasile
    0.45
    Activations Density 0.558%

    No Known Activations