© 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. 5-CLT-HP
    7. 92389
    Prev
    Next
    INDEX
    Explanations

    more

    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
     Jefus
    -0.74
     Monfieur
    -0.71
     bershka
    -0.67
     normaux
    -0.66
     Majefty
    -0.65
    DockStyle
    -0.63
     engraçadas
    -0.61
     intérêt
    -0.60
     myſelf
    -0.59
     scolaires
    -0.59
    POSITIVE LOGITS
     likely
    0.74
     specifically
    0.51
     probably
    0.51
    #+#
    0.50
     certainly
    0.50
     precisely
    0.49
     surely
    0.49
     importantly
    0.48
     agrí
    0.47
     re
    0.47
    Activations Density 0.003%

    No Known Activations