© 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. 44052
    Prev
    Next
    INDEX
    Explanations

    medical 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
     itſelf
    -1.19
     Normdatei
    -1.10
     незавершена
    -1.07
     Majefty
    -1.06
     antibiotics
    -1.04
     reaſon
    -1.04
     nakalista
    -1.04
     EconPapers
    -1.03
     pleaſure
    -1.02
     faſt
    -1.01
    POSITIVE LOGITS
     such
    0.82
    .
    0.80
     in
    0.79
     are
    0.78
     for
    0.77
     that
    0.74
    ,
    0.74
     of
    0.73
     from
    0.69
     and
    0.68
    Activations Density 0.361%

    No Known Activations