© 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. 4-CLT-HP
    7. 3269
    Prev
    Next
    INDEX
    Explanations

    technical documents and code

    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
    meia
    -0.46
     directement
    -0.44
     Whether
    -0.43
    ņas
    -0.43
     WHETHER
    -0.42
    jestic
    -0.42
     seventh
    -0.42
    žni
    -0.42
     متعلقه
    -0.42
    pollo
    -0.41
    POSITIVE LOGITS
     дописавши
    0.71
    CloseOperation
    0.66
    Referencies
    0.66
    Билгалдахарш
    0.64
    Hozzáférés
    0.64
    NameInMap
    0.63
     ویکی‌پدیا
    0.60
    Климат
    0.59
    <bos>
    0.59
    Rujuakan
    0.59
    Activations Density 0.001%

    No Known Activations