© 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. 4960
    Prev
    Next
    INDEX
    Explanations

    prayers

    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
     ComVisible
    -0.90
     kasarigan
    -0.80
     Administrativna
    -0.66
     للاسماء
    -0.65
     Савезне
    -0.61
    
    -0.58
    ValueGeneration
    -0.57
    AndEndTag
    -0.57
    odils
    -0.56
     /\.
    -0.54
    POSITIVE LOGITS
     to
    0.74
     request
    0.68
     for
    0.62
     requests
    0.59
     wheel
    0.59
     Asking
    0.57
     requesting
    0.57
     asked
    0.56
     demandé
    0.56
     către
    0.54
    Activations Density 0.000%

    No Known Activations