© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 38790
    Prev
    Next
    INDEX
    Explanations

    complexity

    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
     complex
    -1.16
     complexity
    -1.13
     compleja
    -1.11
    ArrowToggle
    -1.08
    InjectAttribute
    -1.06
     complejidad
    -1.05
     compless
    -1.01
     complejos
    -1.01
    complex
    -0.96
    Complex
    -0.95
    POSITIVE LOGITS
     byg
    0.50
    chero
    0.49
    lu
    0.47
    gal
    0.46
     artificial
    0.46
     kon
    0.45
    Gön
    0.45
    dt
    0.45
     false
    0.44
    lasses
    0.44
    Activations Density 0.082%

    No Known Activations