© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 16058
    Prev
    Next
    INDEX
    Explanations

    to

    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
    Negative Logits
     to
    -0.66
    ↵↵
    -0.42
     To
    -0.41
     ná
    -0.39
     
    -0.39
     for
    -0.38
     T
    -0.36
     (
    -0.35
     coming
    -0.34
    мал
    -0.34
    POSITIVE LOGITS
    RenderAtEndOf
    1.13
     MainAxisSize
    1.02
     متعلقه
    1.02
     }}$}
    0.99
    IUrlHelper
    0.90
     الحره
    0.90
    onAttach
    0.88
    GraphicsUnit
    0.86
    Hochspringen
    0.85
    ValueStyle
    0.85
    Activations Density 0.009%

    No Known Activations