© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97650
    Prev
    Next
    INDEX
    Explanations

    machines and electricity

    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
     cemeteries
    -0.70
    msgTypes
    -0.68
    WebVitals
    -0.67
     endowments
    -0.65
     breweries
    -0.64
     monasteries
    -0.64
     quarries
    -0.63
     morgue
    -0.62
    DoubleQuotes
    -0.60
    TypedDataSet
    -0.60
    POSITIVE LOGITS
     pressure
    0.54
     roll
    0.52
     voltaje
    0.47
     sensor
    0.47
     lever
    0.44
     current
    0.44
     voltage
    0.43
    hwar
    0.43
     regulator
    0.43
    enste
    0.43
    Activations Density 0.003%

    No Known Activations