© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4073
    Prev
    Next
    INDEX
    Explanations

    web pages and applications

    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
    +#+#
    -1.06
    NOPQRST
    -0.83
     оригіналу
    -0.77
    Personendaten
    -0.77
    InvalidProtocol
    -0.77
    enumi
    -0.69
    DoubleQuotes
    -0.69
     ujednoznacz
    -0.68
    uxxxx
    -0.67
     betweenstory
    -0.67
    POSITIVE LOGITS
     each
    0.49
     cheerfully
    0.47
    rsiniz
    0.47
     fontos
    0.45
     löyty
    0.44
     blancas
    0.42
     Cambio
    0.42
     ilmo
    0.42
    zczegól
    0.42
     ajuns
    0.42
    Activations Density 0.008%

    No Known Activations