© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5941
    Prev
    Next
    INDEX
    Explanations

    medical research

    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
     gomma
    -0.50
    Completion
    -0.49
     Massive
    -0.47
     án
    -0.47
     lateinit
    -0.46
    geta
    -0.45
    СЬ
    -0.44
     funcionales
    -0.44
    conio
    -0.44
    userdetails
    -0.44
    POSITIVE LOGITS
    TagMode
    0.81
    parsedMessage
    0.71
     незавершена
    0.68
    WebControls
    0.68
    AddTagHelper
    0.67
    StoreMessageInfo
    0.63
     nahilalakip
    0.62
    Autoritní
    0.61
    LEncoder
    0.60
    )++;
    0.60
    Activations Density 0.014%

    No Known Activations