© 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. 1-CLT-HP
    7. 295
    Prev
    Next
    INDEX
    Explanations

    macular

    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
    ecare
    -0.82
     macular
    -0.57
    CHAIN
    -0.53
    AccessorTable
    -0.53
    chain
    -0.53
    RectangleBorder
    -0.52
     CITED
    -0.52
     sentenza
    -0.52
    balik
    -0.51
     vendus
    -0.51
    POSITIVE LOGITS
    ########.
    0.63
     AssemblyCulture
    0.57
     ویکی‌پدی
    0.56
    jago
    0.55
     onPostExecute
    0.55
    ății
    0.54
    Personendaten
    0.52
    tvguidetime
    0.52
    ))));
    0.50
    expandindo
    0.49
    Activations Density 0.101%

    No Known Activations