© 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. 43247
    Prev
    Next
    INDEX
    Explanations

    garden/lawn

    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
     garden
    -0.85
     lawn
    -0.77
     Lawn
    -0.77
     gardens
    -0.70
    ants
    -0.67
    lawn
    -0.62
    garden
    -0.59
     Pavilion
    -0.59
     Pav
    -0.58
     pav
    -0.57
    POSITIVE LOGITS
    MLLoader
    0.71
    rrggbb
    0.66
     незавершена
    0.58
     meningitis
    0.56
    !*\
    0.56
    theros
    0.54
     nî
    0.51
    NamedQueries
    0.50
     atherosclerosis
    0.49
     baka
    0.48
    Activations Density 0.915%

    No Known Activations