© 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. 94324
    Prev
    Next
    INDEX
    Explanations

    time/date

    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
    Geplaatst
    -0.97
     ExecuteAsync
    -0.77
    MemoryWarning
    -0.71
    Datuak
    -0.67
     kaarangay
    -0.63
    titleMargin
    -0.62
     beginnetje
    -0.61
    WebServlet
    -0.60
     GenerationType
    -0.57
     AssemblyProduct
    -0.57
    POSITIVE LOGITS
    /*",
    0.55
     each
    0.49
     embreagem
    0.47
    crans
    0.47
     chargés
    0.46
     every
    0.46
    zess
    0.46
    řevě
    0.45
     sebaliknya
    0.45
     escrow
    0.43
    Activations Density 0.018%

    No Known Activations