© 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. 90966
    Prev
    Next
    INDEX
    Explanations

    bacteria and scientific contexts

    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
    rich
    -1.04
    Rich
    -0.82
    PerformLayout
    -0.81
     Wealth
    -0.80
    RICH
    -0.79
     Rich
    -0.78
    Wealth
    -0.77
     richest
    -0.76
     riche
    -0.75
     rich
    -0.74
    POSITIVE LOGITS
    y
    0.91
    s
    0.71
    клопе
    0.65
    scape
    0.59
    ی
    0.56
    shire
    0.54
    er
    0.52
    talk
    0.52
    i
    0.52
    ed
    0.51
    Activations Density 0.069%

    No Known Activations