© 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. 44223
    Prev
    Next
    INDEX
    Explanations

    medical/scientific texts

    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
    aneous
    -1.15
    ValueStyle
    -1.13
    MessageTagHelper
    -0.93
    LabelTagHelper
    -0.86
     незавершена
    -0.86
    UnsafeEnabled
    -0.86
     lenker
    -0.84
     سكانية
    -0.81
    RegressionTest
    -0.80
     betweenstory
    -0.79
    POSITIVE LOGITS
    GeneratedCode
    0.51
    ic
    0.43
    i
    0.42
    al
    0.42
    iecie
    0.41
    Насе
    0.41
     hyper
    0.41
    льт
    0.40
    Hướng
    0.40
    eric
    0.40
    Activations Density 1.663%

    No Known Activations