© 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. 90924
    Prev
    Next
    INDEX
    Explanations

    of

    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
     الحره
    -0.59
     cérami
    -0.58
     muligt
    -0.56
    tagHelperRunner
    -0.56
     humains
    -0.56
     hendes
    -0.55
     rencontré
    -0.55
     priorité
    -0.54
     vicenda
    -0.54
     umano
    -0.53
    POSITIVE LOGITS
    bootstrapcdn
    0.54
     []:
    0.52
    feldt
    0.52
    denly
    0.51
    Portály
    0.50
     BoxDecoration
    0.49
    otherapy
    0.49
     surla
    0.49
     Moran
    0.49
     Tad
    0.48
    Activations Density 0.007%

    No Known Activations