© 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. 43999
    Prev
    Next
    INDEX
    Explanations

    finance and trading

    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
     disambiguazione
    -0.93
     MonoBehaviour
    -0.90
    Życiorys
    -0.89
    bootstrapcdn
    -0.89
    SharedDtor
    -0.88
    lgari
    -0.87
     &___
    -0.86
     мәкал
    -0.85
     Signalez
    -0.84
    NameInMap
    -0.84
    POSITIVE LOGITS
    k
    0.66
    которые
    0.65
    y
    0.62
    t
    0.61
    g
    0.60
    n
    0.59
    v
    0.58
    ye
    0.57
    o
    0.56
    ity
    0.56
    Activations Density 0.076%

    No Known Activations