© 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. 45051
    Prev
    Next
    INDEX
    Explanations

    Medical terminology

    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
    Personendaten
    -0.57
    enetrable
    -0.49
     Against
    -0.49
     olaca
    -0.47
     Mifflin
    -0.46
     neuro
    -0.46
     kasarigan
    -0.46
    findpost
    -0.45
     mostrarán
    -0.44
    Against
    -0.43
    POSITIVE LOGITS
    odyne
    0.68
    />";
    0.67
    httphttps
    0.64
     }</
    0.64
    dram
    0.62
    }}$\\
    0.60
    })`
    0.60
    gonic
    0.60
    ſy
    0.60
     />";
    0.59
    Activations Density 1.607%

    No Known Activations