Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 396
    Prev
    Next
    INDEX
    Explanations

    festivals and events

    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
     tie
    -0.54
     tied
    -0.51
     to
    -0.48
     at
    -0.47
    fest
    -0.47
    reactivex
    -0.45
     in
    -0.44
     chart
    -0.42
    +#+#
    -0.41
     constant
    -0.40
    POSITIVE LOGITS
     мәкал
    0.71
    Personensuche
    0.70
     تضيفلها
    0.69
     дописавши
    0.69
    الحياه
    0.69
    تقاوى
    0.67
    ing
    0.66
    istoitu
    0.66
    odeficiency
    0.65
    ########.
    0.64
    Activations Density 1.620%

    No Known Activations