© 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. 78283
    Prev
    Next
    INDEX
    Explanations

    the

    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
     defendants
    -0.84
     plaintiffs
    -0.83
     villagers
    -0.80
     surgeons
    -0.80
     contestants
    -0.78
     prisoners
    -0.77
     petitioners
    -0.76
     schoolchildren
    -0.76
     colonists
    -0.76
     inmates
    -0.74
    POSITIVE LOGITS
     ComVisible
    0.66
    脚注の使い方
    0.57
    DrawerToggle
    0.56
    Спољашње
    0.54
    tagHelperRunner
    0.53
     estekak
    0.50
    قایناقلار
    0.50
     IActionResult
    0.49
    SBATCH
    0.49
    <bos>
    0.49
    Activations Density 0.002%

    No Known Activations