© 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. 90801
    Prev
    Next
    INDEX
    Explanations

    Ingredients in products/studies

    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
     فريبيس
    -0.90
     Cream
    -0.90
     myſelf
    -0.89
     cream
    -0.86
    GEBURTSDATUM
    -0.85
     Jefus
    -0.84
    matics
    -0.79
     Monfieur
    -0.78
     ſmall
    -0.78
     themſelves
    -0.77
    POSITIVE LOGITS
    iem
    0.54
    quelize
    0.51
    le
    0.50
    Sklici
    0.49
     che
    0.47
    ard
    0.47
    رو
    0.47
     u
    0.47
    lek
    0.45
    <?
    0.45
    Activations Density 0.362%

    No Known Activations