© 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. 95639
    Prev
    Next
    INDEX
    Explanations

    programming and design

    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
    rath
    -0.63
     Kan
    -0.56
     proofs
    -0.56
    ly
    -0.54
     Mariana
    -0.54
    oke
    -0.52
    hner
    -0.48
    參
    -0.48
    ting
    -0.47
    s
    -0.47
    POSITIVE LOGITS
    رشف
    0.73
     gynhyrchwyd
    0.67
    />";
    0.67
    KURZBESCHREIBUNG
    0.65
    +#+#
    0.65
     насељу
    0.63
    +:+
    0.61
     незавершена
    0.60
     विश्वसनीयता
    0.60
     дописавши
    0.59
    Activations Density 1.003%

    No Known Activations