© 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. 5-CLT-HP
    7. 1169
    Prev
    Next
    INDEX
    Explanations

    medical conditions/terminology

    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
     betweenstory
    -0.86
    SequentialGroup
    -0.71
     تضيفلها
    -0.71
    SourceChecksum
    -0.66
    ValueStyle
    -0.66
     الدولى
    -0.65
    posedge
    -0.59
    Портал
    -0.58
    thâu
    -0.57
    曖昧さ回避
    -0.57
    POSITIVE LOGITS
     Exactos
    0.46
    COGN
    0.45
    reveal
    0.44
    color
    0.43
     Cura
    0.43
     Ras
    0.43
    Ras
    0.42
    simple
    0.42
    closed
    0.42
     hien
    0.42
    Activations Density 0.001%

    No Known Activations