© 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. 45788
    Prev
    Next
    INDEX
    Explanations

    medical record review

    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
     &
    -0.48
    <eos>
    -0.41
    ...
    -0.41
     Haupts
    -0.41
    ,
    -0.41
    ↵
    -0.41
    em
    -0.40
    han
    -0.39
    </b>
    -0.36
     and
    -0.36
    POSITIVE LOGITS
     ſeveral
    0.84
     myſelf
    0.84
    addCriterion
    0.83
     EconPapers
    0.81
     themſelves
    0.79
    SpringBootTest
    0.78
     Efq
    0.78
    SharedDtor
    0.78
    IsMutable
    0.76
    providedIn
    0.76
    Activations Density 0.057%

    No Known Activations