© 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. 91203
    Prev
    Next
    INDEX
    Explanations

    has

    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
     vœux
    -0.82
    httphttps
    -0.79
    cemment
    -0.79
     tombé
    -0.74
    herself
    -0.73
     ainfi
    -0.71
     émotions
    -0.71
     enfans
    -0.70
     lèvres
    -0.70
    
    -0.70
    POSITIVE LOGITS
     its
    0.81
     at
    0.47
     different
    0.46
     seats
    0.46
     creators
    0.44
     producers
    0.44
     pens
    0.42
     actors
    0.41
     slightly
    0.41
    toBeDefined
    0.40
    Activations Density 0.001%

    No Known Activations