© 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. 6329
    Prev
    Next
    INDEX
    Explanations

    coded

    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
    holdet
    -0.58
     käyttää
    -0.55
     légal
    -0.54
     legge
    -0.54
    gestellt
    -0.52
     scattata
    -0.51
     équi
    -0.48
     วาด
    -0.47
     réalisée
    -0.47
    Kemudian
    -0.47
    POSITIVE LOGITS
     disambiguazione
    0.74
    RegressionTest
    0.72
    tvguidetime
    0.70
    })`
    0.67
    verwijspagina
    0.67
    ')")
    0.65
    
    0.65
    \%)
    0.63
    ]")
    0.63
    Aholisi
    0.63
    Activations Density 0.001%

    No Known Activations