© 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. 90933
    Prev
    Next
    INDEX
    Explanations

    best

    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
     <<<<<<<<<<<<<<
    -0.96
     bezeichneter
    -0.92
     متعلقه
    -0.91
     للمعارف
    -0.87
    AccessorTable
    -0.85
    utilisons
    -0.81
     nahilalakip
    -0.79
    Autoritní
    -0.76
    quelize
    -0.75
     дописавши
    -0.71
    POSITIVE LOGITS
     right
    0.88
     most
    0.74
     best
    0.71
     answers
    0.58
    right
    0.56
     things
    0.50
     information
    0.49
     correct
    0.48
     versions
    0.48
     ones
    0.47
    Activations Density 0.002%

    No Known Activations