© 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. 11380
    Prev
    Next
    INDEX
    Explanations

    explain

    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
    matchCondition
    -0.57
    WriteTagHelper
    -0.55
    JsonFormat
    -0.52
     incomplète
    -0.52
    省市镇
    -0.52
    Бахар
    -0.51
    itab
    -0.51
     ivelany
    -0.50
     testigos
    -0.50
     inappropriés
    -0.49
    POSITIVE LOGITS
     kasarigan
    0.69
     كومونز
    0.59
     rospy
    0.55
    /**
    0.53
    مصادر
    0.51
    Framed
    0.51
     onCreateView
    0.50
     figurative
    0.49
     للاسماء
    0.47
     thicknesses
    0.47
    Activations Density 0.003%

    No Known Activations