© 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. 0-CLT-HP
    7. 38802
    Prev
    Next
    INDEX
    Explanations

    medical treatments/launches/deliveries

    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
     draw
    -1.01
     delivery
    -0.75
     launch
    -0.74
     withdrawal
    -0.71
     DRAW
    -0.67
     deliver
    -0.56
    withdrawal
    -0.56
    cstring
    -0.52
    delivery
    -0.51
    fromCharCode
    -0.50
    POSITIVE LOGITS
    +#+#
    0.85
    rungsseite
    0.60
     newBuilder
    0.59
     disambiguazione
    0.58
    dengar
    0.58
    Geplaatst
    0.57
    fromnode
    0.56
     pinulongan
    0.53
    way
    0.52
    TestingModule
    0.52
    Activations Density 0.122%

    No Known Activations