© 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. 96667
    Prev
    Next
    INDEX
    Explanations

    scientific/medical analysis

    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
    HasAnnotation
    -0.49
     remo
    -0.47
     müm
    -0.46
     tell
    -0.45
    orre
    -0.44
    deactivate
    -0.43
    ITIVE
    -0.43
     general
    -0.42
     EconPapers
    -0.42
     Lif
    -0.42
    POSITIVE LOGITS
    WriteTagHelper
    0.94
     дописавши
    0.75
    Sucesor
    0.68
     Réponses
    0.66
    تقاوى
    0.66
    Hauptartikel
    0.62
     Picchu
    0.60
    Бахар
    0.59
     cocks
    0.58
     igneous
    0.57
    Activations Density 0.012%

    No Known Activations