© 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. 5-CLT-HP
    7. 2835
    Prev
    Next
    INDEX
    Explanations

    articles

    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
    contentLoaded
    -0.57
     gbc
    -0.55
     muualla
    -0.52
     conqueror
    -0.51
     Suivez
    -0.50
     paces
    -0.48
     useSelector
    -0.47
     Ceux
    -0.47
     ['$
    -0.46
     bint
    -0.46
    POSITIVE LOGITS
     recent
    0.66
     current
    0.62
     calls
    0.57
     ongoing
    0.53
     growing
    0.52
     a
    0.52
     reciente
    0.52
     present
    0.50
     voks
    0.50
     record
    0.49
    Activations Density 0.005%

    No Known Activations