© 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. 94129
    Prev
    Next
    INDEX
    Explanations

    locations

    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
     D
    -0.52
     City
    -0.50
     R
    -0.47
    ↵
    -0.46
     and
    -0.45
     new
    -0.43
     co
    -0.43
     e
    -0.43
     obicei
    -0.43
     
    -0.43
    POSITIVE LOGITS
     ―――――
    1.00
     ſeveral
    0.91
     myſelf
    0.89
     raiſ
    0.88
     ་་
    0.88
     pleaſure
    0.87
     BoxFit
    0.86
     purpoſe
    0.86
     Majefty
    0.85
     itſelf
    0.85
    Activations Density 0.131%

    No Known Activations