© 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. 91785
    Prev
    Next
    INDEX
    Explanations

    Canada

    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
     esternos
    -0.75
     مشين
    -0.75
    StoryboardSegue
    -0.68
    DataAnnotations
    -0.67
    تقاوى
    -0.63
    ########.
    -0.62
    
    -0.62
     defaultstate
    -0.62
    UrlResolution
    -0.62
    gnore
    -0.61
    POSITIVE LOGITS
     Sun
    0.54
     sun
    0.52
    ril
    0.50
     nawr
    0.47
     county
    0.47
    einander
    0.46
    __":
    0.46
    sun
    0.46
    Sun
    0.45
     SUN
    0.45
    Activations Density 0.002%

    No Known Activations