© 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. 74905
    Prev
    Next
    INDEX
    Explanations

    Code, names, and titles

    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
    antit
    -0.56
    pius
    -0.54
    pil
    -0.50
    kol
    -0.49
     pip
    -0.48
     Dealing
    -0.48
    pip
    -0.47
     Biotechnol
    -0.47
     matplotlib
    -0.47
    fp
    -0.46
    POSITIVE LOGITS
     EconPapers
    0.69
     فريبيس
    0.59
     estimés
    0.58
     beginnetje
    0.55
    JspWriter
    0.51
     cherchés
    0.50
     ivelany
    0.50
     Económica
    0.49
    ilización
    0.49
     transférez
    0.49
    Activations Density 0.002%

    No Known Activations