© 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. 1-CLT-HP
    7. 8707
    Prev
    Next
    INDEX
    Explanations

    Inspired

    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
     prunes
    -0.85
    UrlResolution
    -0.64
    WritableDatabase
    -0.59
    WaitGroup
    -0.54
     enjoyed
    -0.50
     Dud
    -0.49
    Inspired
    -0.49
    ify
    -0.49
    quiao
    -0.47
    ButterKnife
    -0.47
    POSITIVE LOGITS
    NewUrlParser
    0.59
    商品説明
    0.57
    +#+
    0.57
    <bos>
    0.57
    المناصب
    0.57
    career
    0.54
    hoeddwyd
    0.54
    CloseOperation
    0.53
     emplois
    0.50
     Posi
    0.50
    Activations Density 0.011%

    No Known Activations