© 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. 6123
    Prev
    Next
    INDEX
    Explanations

    quantity

    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
     insuffisamment
    -0.81
    sizeCache
    -0.71
    oa̍t
    -0.66
     pinulongan
    -0.66
    ArrowToggle
    -0.63
    parsedMessage
    -0.60
    onViewCreated
    -0.60
     CreateTagHelper
    -0.57
    ########.
    -0.57
     Strategic
    -0.55
    POSITIVE LOGITS
    money
    0.66
     money
    0.66
    Money
    0.61
     to
    0.56
     for
    0.55
     dinheiro
    0.53
     Money
    0.49
     concorso
    0.47
     MONEY
    0.47
    钱
    0.47
    Activations Density 0.001%

    No Known Activations