© 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. 95708
    Prev
    Next
    INDEX
    Explanations

    starting or structure

    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
     plan
    -1.50
     Plan
    -0.86
    plan
    -0.80
    Plan
    -0.71
     plane
    -0.69
     план
    -0.68
    s
    -0.68
     planned
    -0.66
    计划
    -0.65
     planen
    -0.65
    POSITIVE LOGITS
     myſelf
    1.05
     Theſe
    1.02
     resourceCulture
    1.00
    IntoConstraints
    0.98
     Efq
    0.97
     itſelf
    0.95
     مشين
    0.94
     Reſ
    0.91
     Anſ
    0.91
     himſelf
    0.90
    Activations Density 0.186%

    No Known Activations