© 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. 0-CLT-HP
    7. 93581
    Prev
    Next
    INDEX
    Explanations

    reflect

    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
     reflected
    -0.92
     CreateTagHelper
    -0.82
     reflecting
    -0.81
    ="@+
    -0.80
     kaarangay
    -0.75
     reflejo
    -0.75
    Reflect
    -0.74
    RectangleBorder
    -0.73
     Reflect
    -0.73
     reflection
    -0.71
    POSITIVE LOGITS
    IsInitialized
    0.51
     inter
    0.50
     station
    0.46
    paedia
    0.45
     ply
    0.45
     getResources
    0.44
    EventArgs
    0.44
    WebElementEntity
    0.44
     motion
    0.43
    ayat
    0.43
    Activations Density 0.159%

    No Known Activations