© 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. 0-CLT-HP
    7. 43799
    Prev
    Next
    INDEX
    Explanations

    notifications

    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
     myſelf
    -1.02
     itſelf
    -0.96
     Theſe
    -0.95
    ſelves
    -0.89
     himſelf
    -0.88
    tagHelperRunner
    -0.87
     themſelves
    -0.86
     AssemblyCulture
    -0.83
     Efq
    -0.82
    ſelf
    -0.82
    POSITIVE LOGITS
     to
    0.56
    onee
    0.52
     Na
    0.48
    みを
    0.47
    /
    0.46
     tính
    0.46
    .
    0.45
    Na
    0.45
    annotation
    0.44
     serving
    0.44
    Activations Density 0.491%

    No Known Activations