© 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. 90457
    Prev
    Next
    INDEX
    Explanations

    iOS

    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
     nakalista
    -0.88
     noDo
    -0.77
     ethical
    -0.76
     ethics
    -0.75
     ethically
    -0.73
     surla
    -0.71
    CloseOperation
    -0.71
    WindowConstants
    -0.69
     morally
    -0.65
     intptr
    -0.65
    POSITIVE LOGITS
    ness
    0.50
    desc
    0.50
    es
    0.50
    ames
    0.48
    s
    0.47
    TargetException
    0.47
     nature
    0.46
    StringValue
    0.46
     Nature
    0.45
    sit
    0.45
    Activations Density 0.312%

    No Known Activations