© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12486
    Prev
    Next
    INDEX
    Explanations

    coupling

    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
     coupling
    -0.71
    coupling
    -0.65
     Coupling
    -0.63
    BeginInit
    -0.55
     ModelAndView
    -0.52
     stanow
    -0.50
     INVENTION
    -0.47
    ature
    -0.46
     sekali
    -0.45
     Réalisation
    -0.45
    POSITIVE LOGITS
    OMB
    0.61
     Paglinawan
    0.59
    ReusableCell
    0.56
    Revenir
    0.55
    omb
    0.54
    laar
    0.54
    утбу
    0.53
    tagHelper
    0.52
     CallOverrides
    0.52
    ogener
    0.51
    Activations Density 0.065%

    No Known Activations