© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93177
    Prev
    Next
    INDEX
    Explanations

    to

    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
    Not in Any Lists

    No Comments

    Negative Logits
     forêts
    -0.48
     lèvres
    -0.47
     épaules
    -0.47
    Odkazy
    -0.44
     guerres
    -0.44
    that
    -0.43
     fidèles
    -0.43
     églises
    -0.43
     oreilles
    -0.43
     surla
    -0.42
    POSITIVE LOGITS
     be
    1.03
    ſelves
    0.79
     raiſ
    0.79
    ſelf
    0.78
     leſs
    0.77
     being
    0.77
     Efq
    0.77
     uſed
    0.75
    wiſe
    0.73
     være
    0.72
    Activations Density 0.001%

    No Known Activations