© 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. 20-CLT-HP
    7. 74894
    Prev
    Next
    INDEX
    Explanations

    technical language/data

    np_max-act-logits · 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
    -1.22
    RenderAtEndOf
    -1.09
    Vidite
    -0.93
    parsedMessage
    -0.88
     '\\;'
    -0.85
    AndEndTag
    -0.85
    ValueStyle
    -0.81
    XmlAccessorType
    -0.78
     initComponents
    -0.74
     beginnetje
    -0.74
    POSITIVE LOGITS
     an
    0.75
     the
    0.71
    Questions
    0.57
     Frage
    0.54
    Question
    0.54
     Question
    0.53
     Questions
    0.52
     вопросов
    0.50
     вопросы
    0.49
     kérdés
    0.49
    Activations Density 0.001%

    No Known Activations