© 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. 607
    Prev
    Next
    INDEX
    Explanations

    clinical

    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
    Tikang
    -0.72
     asiatique
    -0.68
     Meksiku
    -0.67
     Dumnezeu
    -0.66
     supérieures
    -0.66
     élevées
    -0.65
    /***/
    -0.65
     économies
    -0.63
     împre
    -0.62
     supérieurs
    -0.62
    POSITIVE LOGITS
     marks
    0.55
    atte
    0.48
     box
    0.47
     means
    0.45
     marked
    0.44
     Attendance
    0.44
     الحره
    0.42
    Cloudy
    0.42
    cros
    0.41
     cold
    0.40
    Activations Density 0.000%

    No Known Activations