© 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. 4595
    Prev
    Next
    INDEX
    Explanations

    start of new text

    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
     initComponents
    -0.75
     fidé
    -0.64
    WithIOException
    -0.63
     Jefus
    -0.63
    lardır
    -0.62
    ADELPHIA
    -0.61
     فريبيس
    -0.60
     spéciales
    -0.60
    WebServlet
    -0.60
     to
    -0.59
    POSITIVE LOGITS
    锈钢
    0.52
     term
    0.52
     word
    0.49
     phrase
    0.47
     safety
    0.43
    word
    0.43
     Wiktionnaire
    0.43
     ouro
    0.42
     Phrase
    0.42
     quy
    0.42
    Activations Density 0.009%

    No Known Activations