© 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. 8708
    Prev
    Next
    INDEX
    Explanations

    rack

    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
    rack
    -2.55
     rack
    -2.31
     Rack
    -2.17
    Rack
    -2.06
    racks
    -1.87
     racks
    -1.80
     racking
    -1.38
    rak
    -1.16
    racked
    -1.16
     racked
    -1.03
    POSITIVE LOGITS
    日閲覧
    0.90
    yntaxException
    0.75
    expandindo
    0.74
    ]")]
    0.65
     Савезне
    0.65
    مصادر
    0.61
    glTranslatef
    0.61
     propOrder
    0.60
    easter
    0.57
    ette
    0.57
    Activations Density 0.019%

    No Known Activations