© 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. 4-CLT-HP
    7. 1244
    Prev
    Next
    INDEX
    Explanations

    medical

    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
    ⓧ
    -0.84
    principalTable
    -0.70
    prepareStatement
    -0.65
    getColumnIndex
    -0.62
    期刊论文
    -0.61
    IMPORTED
    -0.61
     utafitiHapana
    -0.60
     ſta
    -0.59
    OOTDTY
    -0.58
    Tembelea
    -0.58
    POSITIVE LOGITS
     conditions
    0.68
    conditions
    0.58
    Conditions
    0.56
     Conditions
    0.50
    Importing
    0.44
    eleste
    0.42
     števil
    0.41
     figura
    0.41
    declarations
    0.41
     fields
    0.40
    Activations Density 0.004%

    No Known Activations