© 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. 91932
    Prev
    Next
    INDEX
    Explanations

    medical research

    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
    cted
    -1.03
    ulation
    -1.02
    ulated
    -1.01
    ULATION
    -0.92
    ulations
    -0.91
    transmission
    -0.83
    ulates
    -0.82
    ULATED
    -0.82
     Transmission
    -0.79
     transmission
    -0.75
    POSITIVE LOGITS
    argout
    0.58
    Traceback
    0.54
    hdashline
    0.52
     Gump
    0.51
    )‏
    0.50
    RegistryLite
    0.49
    WriteBarrier
    0.49
    uxxxx
    0.48
    localctx
    0.47
    __))
    0.46
    Activations Density 0.141%

    No Known Activations