© 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. 39899
    Prev
    Next
    INDEX
    Explanations

    scientific/academic topics

    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
    natural
    -1.13
     naturelle
    -1.08
     naturale
    -1.04
    naturally
    -1.04
    NATURAL
    -1.03
     naturali
    -1.02
     naturalmente
    -1.01
     natuurlijke
    -1.00
     naturlig
    -0.99
     naturels
    -0.94
    POSITIVE LOGITS
    ist
    0.74
    istic
    0.70
    IST
    0.58
    ism
    0.56
     inf
    0.55
    ists
    0.52
    ISTIC
    0.51
    er
    0.50
     Life
    0.49
    gol
    0.49
    Activations Density 0.049%

    No Known Activations