© 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. 0-CLT-HP
    7. 45412
    Prev
    Next
    INDEX
    Explanations

    popular

    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
     Popular
    -1.00
     Luce
    -0.75
     plan
    -0.57
    dek
    -0.57
    Popular
    -0.53
    ben
    -0.52
     les
    -0.48
     ces
    -0.47
     Westminster
    -0.45
    helen
    -0.45
    POSITIVE LOGITS
     utafitiHapana
    0.86
     Theſe
    0.79
     Monfieur
    0.75
     Inſ
    0.74
     kasarigan
    0.71
     Anſ
    0.71
     Houſe
    0.70
    TagHelper
    0.70
     fidé
    0.70
     Majefty
    0.70
    Activations Density 1.699%

    No Known Activations