© 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. 98217
    Prev
    Next
    INDEX
    Explanations

    half

    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
     half
    -0.69
     to
    -0.61
     W
    -0.51
    half
    -0.49
     over
    -0.47
     
    -0.46
     (
    -0.45
     on
    -0.43
     ‘
    -0.42
     F
    -0.41
    POSITIVE LOGITS
     myſelf
    1.10
     betweenstory
    1.10
     itſelf
    1.07
     Jefus
    1.06
    AccessorTable
    1.02
    IUrlHelper
    1.01
     uſed
    1.01
     Theſe
    0.99
     themſelves
    0.97
     Савезне
    0.97
    Activations Density 0.000%

    No Known Activations