© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12508
    Prev
    Next
    INDEX
    Explanations

    archive

    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
    strument
    -0.70
     Reverso
    -0.67
    uesday
    -0.66
    matsu
    -0.65
     تضيفلها
    -0.64
    aboo
    -0.64
    SpringRunner
    -0.63
     archive
    -0.62
    AddTagHelper
    -0.60
     archival
    -0.60
    POSITIVE LOGITS
    +#+#
    0.46
     of
    0.45
     виправивши
    0.43
    ViewImports
    0.40
     communs
    0.39
    OfWork
    0.39
     fundación
    0.38
     Besuch
    0.38
     contient
    0.38
    ones
    0.37
    Activations Density 0.002%

    No Known Activations