© 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. 1945
    Prev
    Next
    INDEX
    Explanations

    above

    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
     purpoſe
    -0.77
     perfons
    -0.75
    OGND
    -0.75
     kasarigan
    -0.73
     uſed
    -0.71
    NOPQRST
    -0.70
    rungsseite
    -0.69
    Personensuche
    -0.69
    NameInMap
    -0.68
     chiave
    -0.67
    POSITIVE LOGITS
    /
    0.52
    “
    0.48
     experimentally
    0.48
     Arduino
    0.47
     Experiment
    0.46
    ™
    0.45
    "
    0.44
    *
    0.44
     Conclusion
    0.44
     /
    0.43
    Activations Density 0.050%

    No Known Activations