© 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. 411
    Prev
    Next
    INDEX
    Explanations

    reading data/information

    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
     read
    -0.85
    Read
    -0.71
    read
    -0.70
     reading
    -0.70
     Read
    -0.67
     READ
    -0.60
     lettura
    -0.58
     leitura
    -0.57
     membaca
    -0.57
    READ
    -0.56
    POSITIVE LOGITS
    siella
    0.69
     reductase
    0.69
     hypothalamus
    0.65
     capillaries
    0.63
     glandular
    0.63
    rangea
    0.62
    athyroid
    0.62
    obacteria
    0.62
     pituitary
    0.61
    CrossRef
    0.61
    Activations Density 0.027%

    No Known Activations