© 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. 8997
    Prev
    Next
    INDEX
    Explanations

    qu

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Misa
    -0.56
     worn
    -0.53
     Normandie
    -0.52
    لينكات
    -0.52
     Stoner
    -0.52
     Layla
    -0.51
    டை
    -0.50
     Hati
    -0.48
     Worn
    -0.48
    گا
    -0.48
    POSITIVE LOGITS
     AssemblyCulture
    0.60
     незавершена
    0.59
    ]")]
    0.57
    reportWebVitals
    0.56
     @"/
    0.56
    windowFixed
    0.54
    ISupport
    0.54
     препратки
    0.54
     '{@
    0.52
     ويكيپيديا
    0.52
    Activations Density 0.012%

    No Known Activations