© 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. 1817
    Prev
    Next
    INDEX
    Explanations

    how

    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
     how
    -2.28
    how
    -1.99
    How
    -1.62
     cómo
    -1.52
     bagaimana
    -1.50
     How
    -1.46
     hvordan
    -1.34
    HOW
    -1.25
    what
    -1.10
    如何
    -1.09
    POSITIVE LOGITS
     they
    0.91
    จึง
    0.87
     dAtA
    0.85
     getItemId
    0.84
    soever
    0.82
     much
    0.81
     else
    0.81
     many
    0.81
     we
    0.79
     you
    0.79
    Activations Density 0.222%

    No Known Activations