© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92025
    Prev
    Next
    INDEX
    Explanations

    science/technical

    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
    grow
    -0.51
    DoubleQuotes
    -0.50
    IsContent
    -0.48
    ASKA
    -0.48
     خارجية
    -0.47
    ritic
    -0.43
    EventLoop
    -0.43
     Paglinawan
    -0.43
     '\\;'
    -0.43
     متعلقه
    -0.43
    POSITIVE LOGITS
    titleMargin
    0.51
    IndentedString
    0.51
    ParallelGroup
    0.51
    OrNil
    0.50
     intptr
    0.49
    KX
    0.49
     plugged
    0.46
    shore
    0.46
     pivo
    0.46
     capped
    0.45
    Activations Density 0.001%

    No Known Activations