© 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. 91548
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
     actualidad
    -0.58
     désormais
    -0.55
    AntiForgeryToken
    -0.51
    ède
    -0.51
     quelcon
    -0.47
     maintenant
    -0.47
     pido
    -0.46
     שוליים
    -0.46
     épisodes
    -0.46
     índice
    -0.45
    POSITIVE LOGITS
    تقاوى
    0.63
     otomatig
    0.61
    endphp
    0.60
     most
    0.57
    sierten
    0.55
    WriteTagHelper
    0.54
     nakalista
    0.54
    yarnpkg
    0.52
    TestingModule
    0.52
     فريبيس
    0.51
    Activations Density 0.002%

    No Known Activations