© 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. 91121
    Prev
    Next
    INDEX
    Explanations

    encyclopedia entries

    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
     espagne
    -0.56
     Connectez
    -0.55
     occhiali
    -0.55
     Ajoutez
    -0.53
     régionale
    -0.52
    kloped
    -0.52
     étrangère
    -0.51
     oignon
    -0.51
     végétale
    -0.50
     Asegúrese
    -0.50
    POSITIVE LOGITS
    ]--;
    0.61
     שוליים
    0.54
    
    0.53
    <?
    0.53
    )))));
    0.52
    WriteLiteral
    0.51
     kasarigan
    0.50
    Referenties
    0.49
     跳转至
    0.49
    bonucleic
    0.48
    Activations Density 0.023%

    No Known Activations