© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1200
    Prev
    Next
    INDEX
    Explanations

    union

    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
     Union
    -0.88
    UNION
    -0.75
    Union
    -0.69
    signal
    -0.68
     UNION
    -0.67
    Signal
    -0.64
     Signal
    -0.64
     signal
    -0.63
     SIGNAL
    -0.59
    Signals
    -0.57
    POSITIVE LOGITS
    parsedMessage
    0.85
    ViewFeatures
    0.82
    клопе
    0.81
    WebVitals
    0.77
    Vidite
    0.75
    تقاوى
    0.70
     otomatig
    0.68
    AndEndTag
    0.68
    IBOutlet
    0.67
    ChildScrollView
    0.66
    Activations Density 0.203%

    No Known Activations