© 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. 5-CLT-HP
    7. 6196
    Prev
    Next
    INDEX
    Explanations

    the

    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
    ChildScrollView
    -0.68
    ReusableCell
    -0.68
    UIControlState
    -0.65
    AddTagHelper
    -0.63
     contextLoads
    -0.63
    /*
    -0.61
    another
    -0.60
     another
    -0.59
     Seorang
    -0.59
     utafitiHapana
    -0.58
    POSITIVE LOGITS
     often
    0.58
     rarely
    0.56
    often
    0.53
     usually
    0.53
    phenomen
    0.51
     Often
    0.50
    meist
    0.49
    usually
    0.49
     rare
    0.49
     oftentimes
    0.48
    Activations Density 0.006%

    No Known Activations