© 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. 0-CLT-HP
    4. 38449
    Prev
    Next
    INDEX
    Explanations

    medical contexts

    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
     Lee
    -0.72
     lee
    -0.61
    Lee
    -0.59
    CloseOperation
    -0.58
     LEE
    -0.55
     Phi
    -0.51
    iconque
    -0.47
    sidemargin
    -0.44
    syscall
    -0.44
     Swiss
    -0.43
    POSITIVE LOGITS
     Efq
    0.85
     Anſ
    0.81
    Билгалдахарш
    0.79
    ########.
    0.79
     Conſ
    0.78
     Reſ
    0.77
     Majefty
    0.76
     Houſe
    0.75
    ſelf
    0.72
     Perſ
    0.70
    Activations Density 0.096%

    No Known Activations