© 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. 2470
    Prev
    Next
    INDEX
    Explanations

    of

    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
    makeConstraints
    -0.73
    tamol
    -0.52
    تقاوى
    -0.52
     Pharmaco
    -0.52
     betweenstory
    -0.51
    etal
    -0.51
    AutoresizingMask
    -0.50
     fumar
    -0.48
    RenderAtEndOf
    -0.48
    الحياه
    -0.47
    POSITIVE LOGITS
     lenker
    0.69
    TURE
    0.52
    acité
    0.51
     خارجية
    0.50
     löytyy
    0.48
    AddTagHelper
    0.47
    Specifiche
    0.47
    AndroidJUnit
    0.47
    IFICATIONS
    0.46
    ALLED
    0.46
    Activations Density 0.009%

    No Known Activations