© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2228
    Prev
    Next
    INDEX
    Explanations

    ICU care

    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
     Efq
    -0.59
    EndGlobalSection
    -0.54
    nextState
    -0.53
     Eſ
    -0.52
    ệu
    -0.52
    HasForeignKey
    -0.51
    úrese
    -0.50
    enoord
    -0.50
    Filmografie
    -0.50
     Pelop
    -0.49
    POSITIVE LOGITS
     nurses
    0.67
     nurse
    0.62
     Nurses
    0.60
     saites
    0.55
    didSet
    0.55
     transport
    0.54
     Transport
    0.54
     rooms
    0.53
    Transport
    0.52
     '\\;'
    0.52
    Activations Density 0.004%

    No Known Activations