© 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. 20-CLT-HP
    7. 78145
    Prev
    Next
    INDEX
    Explanations

    Code and technical language

    np_max-act-logits · 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
     propOrder
    -0.62
     ddelweddau
    -0.61
    exels
    -0.59
    ummies
    -0.56
    MLLoader
    -0.55
     <=",
    -0.55
    UnusedPrivate
    -0.54
     Plots
    -0.54
     @"/
    -0.53
    WriteTagHelper
    -0.53
    POSITIVE LOGITS
    __(/*!
    0.58
    RemoveField
    0.57
     plan
    0.52
    !*\
    0.52
    quelize
    0.51
     deal
    0.49
     base
    0.49
    plan
    0.48
    base
    0.48
    deal
    0.48
    Activations Density 0.000%

    No Known Activations