© 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. 95519
    Prev
    Next
    INDEX
    Explanations

    inception

    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
     Technologies
    -0.98
    Technologies
    -0.90
     technologies
    -0.87
     TECHNOLOGIES
    -0.80
    technologies
    -0.76
    enumi
    -0.71
    
    -0.67
     cherchés
    -0.62
    BagLayout
    -0.61
     inception
    -0.61
    POSITIVE LOGITS
     of
    0.61
    łaj
    0.61
    te
    0.54
    es
    0.50
    alone
    0.50
    king
    0.49
    less
    0.49
    let
    0.46
    dor
    0.45
    zob
    0.45
    Activations Density 0.081%

    No Known Activations