© 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. 71472
    Prev
    Next
    INDEX
    Explanations

    you

    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
     Chriftian
    -0.86
     étoit
    -0.82
     purpoſe
    -0.80
     Efq
    -0.80
     auroit
    -0.79
     venons
    -0.78
     médicale
    -0.77
     Monfieur
    -0.76
     quæ
    -0.76
     avoient
    -0.75
    POSITIVE LOGITS
     spot
    0.60
     step
    0.60
     make
    0.60
     emerge
    0.48
    XmlAccessorType
    0.46
     dis
    0.45
     p
    0.45
    ipur
    0.44
     reach
    0.43
     stand
    0.43
    Activations Density 0.000%

    No Known Activations