© 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. 95601
    Prev
    Next
    INDEX
    Explanations

    publication

    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
     composition
    -1.05
    composition
    -1.02
     Composition
    -0.95
    Composition
    -0.91
     compositions
    -0.85
     publication
    -0.84
     COMPOSITION
    -0.83
    Publication
    -0.77
     GenerationType
    -0.75
     Publication
    -0.74
    POSITIVE LOGITS
    ality
    0.57
    <bos>
    0.53
     Paroles
    0.51
    pping
    0.49
    sional
    0.49
    ally
    0.48
    atorial
    0.48
    multer
    0.47
     Bureau
    0.47
    nodejs
    0.46
    Activations Density 0.282%

    No Known Activations