© 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. 4383
    Prev
    Next
    INDEX
    Explanations

    international/global

    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
     dia
    -0.52
    sizeCache
    -0.50
    SharedCtor
    -0.47
    AsUp
    -0.47
     CH
    -0.43
    saraba
    -0.42
     שהוא
    -0.42
    ನ್ನು
    -0.42
    :✨
    -0.42
     cual
    -0.42
    POSITIVE LOGITS
     parlato
    0.62
     Akismet
    0.60
    Réalisation
    0.59
     célèbres
    0.58
     adquirido
    0.57
     lavorato
    0.57
     loob
    0.57
     vendido
    0.55
     dolomite
    0.55
     vectorielles
    0.54
    Activations Density 0.001%

    No Known Activations