© 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. 1-CLT-HP
    7. 12161
    Prev
    Next
    INDEX
    Explanations

    stem cell reprogramming/opioids

    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
     myſelf
    -1.07
     Monfieur
    -1.05
    脚注の使い方
    -0.95
     Efq
    -0.95
     تانيه
    -0.93
     ſeveral
    -0.91
     leſs
    -0.90
    ſelf
    -0.90
     raiſ
    -0.90
     estekak
    -0.88
    POSITIVE LOGITS
    ing
    0.70
    ed
    0.57
    s
    0.55
    ↵
    0.54
    a
    0.50
    '
    0.50
    est
    0.50
    ting
    0.48
     D
    0.48
     S
    0.48
    Activations Density 0.027%

    No Known Activations