© 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. 0-CLT-HP
    7. 95605
    Prev
    Next
    INDEX
    Explanations

    helped

    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
    helped
    -0.89
     gave
    -0.80
     helped
    -0.80
     contribué
    -0.73
     ayudó
    -0.69
     Helped
    -0.68
     hjäl
    -0.63
    gave
    -0.63
    featureID
    -0.62
     permitió
    -0.60
    POSITIVE LOGITS
     them
    0.79
    تقاوى
    0.73
     inside
    0.70
     taken
    0.68
     cref
    0.68
     createState
    0.66
    WebServlet
    0.64
     change
    0.64
    httphttps
    0.64
     unknownFields
    0.63
    Activations Density 0.075%

    No Known Activations