© 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. 5767
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    CloseOperation
    -0.80
     يتيمه
    -0.72
     وتسجيلات
    -0.64
    jedis
    -0.63
    UnsafeEnabled
    -0.59
     defaultstate
    -0.57
    complexType
    -0.57
    WriteBarrier
    -0.56
     CWE
    -0.56
     verle
    -0.54
    POSITIVE LOGITS
    #
    0.79
     EconPapers
    0.76
    cshtml
    0.71
    Rujuakan
    0.58
    /*
    0.54
    BeginInit
    0.49
     казалось
    0.49
    //
    0.49
    ISupport
    0.49
     initComponents
    0.49
    Activations Density 0.008%

    No Known Activations