© 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. 0-CLT-HP
    7. 93892
    Prev
    Next
    INDEX
    Explanations

    life

    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
     
    -0.68
     an
    -0.65
     a
    -0.63
     (
    -0.62
     P
    -0.62
     or
    -0.62
     in
    -0.61
    i
    -0.61
     k
    -0.59
    -
    -0.58
    POSITIVE LOGITS
     Majefty
    1.10
     Anſ
    1.09
     Efq
    1.06
     Monfieur
    1.04
    WithIOException
    1.02
     myſelf
    1.01
     themſelves
    0.99
     ſeveral
    0.97
     Reſ
    0.95
     itſelf
    0.95
    Activations Density 0.240%

    No Known Activations