Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 3807
    Prev
    Next
    INDEX
    Explanations

    scientific writing

    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
    TypedDataSet
    -0.84
     насељу
    -0.77
     brune
    -0.73
     EconPapers
    -0.71
     whoſe
    -0.70
     Monfieur
    -0.69
     ſmall
    -0.66
    OGND
    -0.66
     Générale
    -0.65
    niająca
    -0.65
    POSITIVE LOGITS
    ulously
    0.66
    ically
    0.65
    ously
    0.65
    tually
    0.64
    ually
    0.63
    nically
    0.62
    ally
    0.61
    sively
    0.59
    tiously
    0.57
    uously
    0.57
    Activations Density 0.018%

    No Known Activations