© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4462
    Prev
    Next
    INDEX
    Explanations

    expressing certainty

    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
    findpost
    -0.90
    Datuak
    -0.83
    +#+#
    -0.78
    UserScript
    -0.70
    évaluateur
    -0.68
    MessageOf
    -0.66
     EconPapers
    -0.65
    AndEndTag
    -0.63
    </caption>
    -0.62
    Filmografia
    -0.61
    POSITIVE LOGITS
    acaktır
    0.51
     major
    0.50
     مستقیم
    0.48
     winner
    0.48
     bezpośrednio
    0.48
     Gewinner
    0.48
     enormous
    0.47
     Directly
    0.47
     Obviously
    0.47
    Huge
    0.47
    Activations Density 0.003%

    No Known Activations