© 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. 90852
    Prev
    Next
    INDEX
    Explanations

    battery

    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
     battery
    -0.84
    battery
    -0.76
     batteries
    -0.76
     kasarigan
    -0.73
     batterie
    -0.70
     Battery
    -0.69
    Battery
    -0.66
     ModelExpression
    -0.65
     BATTERY
    -0.65
     bateria
    -0.63
    POSITIVE LOGITS
    PerformLayout
    0.75
     CURIAM
    0.59
     toalha
    0.56
     jobbet
    0.55
     nettoy
    0.53
     laget
    0.52
    جموعة
    0.52
    ioutil
    0.52
     scattata
    0.52
    дъ
    0.50
    Activations Density 0.001%

    No Known Activations