© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 72
    Prev
    Next
    INDEX
    Explanations

    environmentally

    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
     ✭✭
    -0.77
     Efq
    -0.69
    berdayakan
    -0.68
    AnimationsModule
    -0.68
    glLoadIdentity
    -0.66
     Structured
    -0.65
    
    -0.65
     fevere
    -0.65
    ſelf
    -0.65
    IBOutlet
    -0.65
    POSITIVE LOGITS
    -
    0.57
    bug
    0.41
    do
    0.39
    tock
    0.38
    mybatisplus
    0.37
    ouder
    0.35
     hul
    0.35
    chart
    0.35
    b
    0.34
     bug
    0.34
    Activations Density 0.000%

    No Known Activations