© 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. 0-CLT-HP
    7. 38431
    Prev
    Next
    INDEX
    Explanations

    farms and cafes

    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
     Farm
    -1.08
     farm
    -1.06
    Farm
    -1.05
    farm
    -0.97
    farms
    -0.97
     warm
    -0.93
     FARM
    -0.93
     Warm
    -0.92
    warm
    -0.92
    Warm
    -0.91
    POSITIVE LOGITS
    ian
    0.72
    ma
    0.69
    ization
    0.66
    ion
    0.65
    ite
    0.63
    let
    0.63
    time
    0.61
    ce
    0.59
    co
    0.58
    land
    0.57
    Activations Density 0.133%

    No Known Activations