© 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. 5-CLT-HP
    7. 94581
    Prev
    Next
    INDEX
    Explanations

    formal and technical text

    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
     EconPapers
    -0.59
     InputDecoration
    -0.59
    IntoConstraints
    -0.58
    出版年
    -0.56
    ChromeDriver
    -0.55
    AndEndTag
    -0.54
    saraba
    -0.54
    存于互联网档案馆
    -0.53
     onResponse
    -0.52
    argli
    -0.52
    POSITIVE LOGITS
     autorytatywna
    0.79
     kasarigan
    0.56
    новништво
    0.54
    važ
    0.51
     the
    0.49
    tional
    0.49
     szint
    0.47
    ển
    0.46
     MediatR
    0.46
     Voice
    0.45
    Activations Density 0.000%

    No Known Activations