© 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. 92120
    Prev
    Next
    INDEX
    Explanations

    radical

    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
     Radical
    -1.13
    radical
    -1.03
     radical
    -0.94
    assembly
    -0.93
    Radical
    -0.91
     radikal
    -0.91
     assembly
    -0.88
    WebServlet
    -0.86
     radicals
    -0.85
     varandra
    -0.82
    POSITIVE LOGITS
    s
    1.00
    ness
    0.73
    y
    0.73
    ی
    0.72
    m
    0.52
    ry
    0.52
    ler
    0.50
     borde
    0.48
    ll
    0.47
    t
    0.46
    Activations Density 0.056%

    No Known Activations