© 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. 1-CLT-HP
    7. 46194
    Prev
    Next
    INDEX
    Explanations

    urgency

    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
    ality
    -0.59
     temporary
    -0.53
    చు
    -0.49
    uban
    -0.48
    (@"%@",
    -0.46
     Error
    -0.46
     mikro
    -0.46
    Vikt
    -0.45
    tema
    -0.45
    ortion
    -0.44
    POSITIVE LOGITS
     propOrder
    0.77
    ResumeLayout
    0.73
     Италијани
    0.71
    PyExc
    0.68
     mouseClicked
    0.58
    @@@@@
    0.57
     OFDb
    0.56
     فريبيس
    0.54
     trajets
    0.54
    complexContent
    0.53
    Activations Density 0.014%

    No Known Activations