© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 39789
    Prev
    Next
    INDEX
    Explanations

    medical studies/procedures

    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
     Milk
    -0.82
    milk
    -0.74
     hâte
    -0.73
    setVerticalGroup
    -0.72
    Milk
    -0.68
     siguran
    -0.66
     milk
    -0.66
    ỡng
    -0.65
     snippetHide
    -0.64
    EDEFAULT
    -0.62
    POSITIVE LOGITS
    ttemberg
    0.59
    iness
    0.58
    Хьажоргаш
    0.57
    <bos>
    0.55
     preparation
    0.51
    efeller
    0.49
     ear
    0.49
     production
    0.49
    rovnik
    0.49
     LUX
    0.48
    Activations Density 0.081%

    No Known Activations