© 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. 94974
    Prev
    Next
    INDEX
    Explanations

    ]]

    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
    icorn
    -0.85
     (
    -0.84
     Y
    -0.70
    hoeddwyd
    -0.67
    edom
    -0.58
    ,
    -0.56
     H
    -0.54
     =
    -0.52
    ↵↵
    -0.51
    ]]
    -0.51
    POSITIVE LOGITS
     pleaſure
    1.05
     myſelf
    0.98
     Monfieur
    0.96
     neceffary
    0.93
     itſelf
    0.93
     Jefus
    0.93
     fevere
    0.92
     faſt
    0.91
     himſelf
    0.90
     ſeveral
    0.86
    Activations Density 1.576%

    No Known Activations