© 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. 40406
    Prev
    Next
    INDEX
    Explanations

    decisions and engineering

    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
    ing
    -0.93
    ING
    -0.65
     point
    -0.64
    oidal
    -0.63
    cing
    -0.62
    ging
    -0.61
    eronau
    -0.56
    rial
    -0.56
    ellular
    -0.55
    forth
    -0.55
    POSITIVE LOGITS
     оригіналу
    0.73
    xnn
    0.72
     disambiguazione
    0.65
     Administrativna
    0.59
     bienven
    0.58
    +#+#
    0.57
     immédi
    0.56
     lèvres
    0.56
     quelcon
    0.56
    parsedMessage
    0.56
    Activations Density 0.494%

    No Known Activations