© 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. 42952
    Prev
    Next
    INDEX
    Explanations

    arent

    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
     pleaſure
    -1.01
     Efq
    -0.99
     myſelf
    -0.98
     Paglinawan
    -0.96
     itſelf
    -0.95
    +#+#
    -0.94
    ViewImports
    -0.94
     purpoſe
    -0.93
     bezeichneter
    -0.92
    StoryboardSegue
    -0.91
    POSITIVE LOGITS
    f
    0.56
    H
    0.54
    ill
    0.52
    ,
    0.52
     
    0.51
    F
    0.49
     in
    0.49
    z
    0.48
    char
    0.48
    co
    0.47
    Activations Density 1.150%

    No Known Activations