© 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. 2374
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    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
     soigneusement
    -0.44
     provisoire
    -0.44
     lourdes
    -0.40
    abuse
    -0.39
     réfugiés
    -0.38
     rétro
    -0.38
     étions
    -0.37
     rü
    -0.37
     Abuse
    -0.37
     يد
    -0.36
    POSITIVE LOGITS
     himſelf
    0.66
     themſelves
    0.65
    opsida
    0.65
     Efq
    0.64
     Cæsar
    0.64
     handleMessage
    0.64
    ]")]
    0.60
     CreateTagHelper
    0.60
     ویکی‌پدیای
    0.60
    nestjs
    0.59
    Activations Density 0.004%

    No Known Activations