© 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. 94421
    Prev
    Next
    INDEX
    Explanations

    code/copyright

    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
     déclarations
    -0.70
     âmes
    -0.59
     mères
    -0.56
     prêtres
    -0.55
     conversión
    -0.55
     privadas
    -0.54
     inconvénients
    -0.54
    zyden
    -0.53
     valoración
    -0.53
     traités
    -0.52
    POSITIVE LOGITS
     resourceCulture
    0.54
     constellations
    0.52
     boxed
    0.50
    Window
    0.48
    al
    0.47
     Sext
    0.46
    boxed
    0.46
     stemmed
    0.46
     defaultdict
    0.45
    Wipe
    0.45
    Activations Density 0.001%

    No Known Activations