© 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. 40062
    Prev
    Next
    INDEX
    Explanations

    Manhattan

    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
     automatiques
    -0.95
     själva
    -0.94
     formales
    -0.94
     vectorielles
    -0.90
     varandra
    -0.90
     quæ
    -0.89
     japonaise
    -0.89
     commerciales
    -0.89
     réguli
    -0.88
     picioare
    -0.88
    POSITIVE LOGITS
    ise
    0.65
    ization
    0.65
    izing
    0.62
     ad
    0.59
     system
    0.56
     app
    0.56
    ism
    0.56
    ized
    0.54
    ize
    0.53
     Ad
    0.53
    Activations Density 0.043%

    No Known Activations