© 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. 15453
    Prev
    Next
    INDEX
    Explanations

    period

    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
     shouldn
    -0.73
     wasn
    -0.72
     wasnt
    -0.69
     isn
    -0.69
     weren
    -0.69
     isnt
    -0.68
     such
    -0.67
     lets
    -0.66
     shouldnt
    -0.66
     whats
    -0.64
    POSITIVE LOGITS
     Heck
    0.62
    Heck
    0.52
     générations
    0.52
     racines
    0.52
     Seriously
    0.52
     phénomènes
    0.52
     enfans
    0.51
    principalTable
    0.50
     Shit
    0.50
     églises
    0.50
    Activations Density 0.007%

    No Known Activations