© 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. 95699
    Prev
    Next
    INDEX
    Explanations

    technical documents/code

    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
    k
    -1.31
    Form
    -0.81
     Form
    -0.75
    GA
    -0.68
     k
    -0.55
    kman
    -0.53
    ais
    -0.47
    y
    -0.47
    Forms
    -0.45
     Forms
    -0.43
    POSITIVE LOGITS
    ########.
    0.79
    TestingModule
    0.77
    stylers
    0.71
    ,:);
    0.71
    ſelf
    0.69
     تضيفلها
    0.66
     betweenstory
    0.66
    modelBuilder
    0.66
    drake
    0.65
    neſs
    0.65
    Activations Density 0.102%

    No Known Activations