© 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. 38689
    Prev
    Next
    INDEX
    Explanations

    blog

    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
     blog
    -1.18
     Blog
    -1.04
     surprise
    -1.00
     surprised
    -0.92
    Blog
    -0.88
     surprising
    -0.85
    blog
    -0.84
     BLOG
    -0.84
     lab
    -0.81
     surprises
    -0.79
    POSITIVE LOGITS
     enfans
    0.73
     purpoſe
    0.63
    ging
    0.61
    bbene
    0.60
     ſeveral
    0.60
     Jefus
    0.59
     houſe
    0.59
     quæ
    0.59
    közi
    0.59
     chofe
    0.59
    Activations Density 0.160%

    No Known Activations