© 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. 20-CLT-HP
    7. 74736
    Prev
    Next
    INDEX
    Explanations

    Low-budget, chemistry

    np_max-act-logits · 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
     Expensive
    -1.03
    Higher
    -1.00
    Highest
    -0.95
    Expensive
    -0.91
     Higher
    -0.89
    higher
    -0.86
     wealthiest
    -0.85
    setVerticalGroup
    -0.85
     Highest
    -0.85
    Высо
    -0.84
    POSITIVE LOGITS
     che
    0.56
     dirt
    0.56
     CHE
    0.54
     Che
    0.52
     ldc
    0.48
     L
    0.47
    L
    0.43
    Che
    0.42
     suspiciously
    0.40
     goed
    0.39
    Activations Density 0.001%

    No Known Activations