© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 918
    Prev
    Next
    INDEX
    Explanations

    unknown

    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
    DockStyle
    -0.63
     tartalomajánló
    -0.52
    日閲覧
    -0.52
     Вікі
    -0.50
    談社
    -0.47
    ellini
    -0.44
     Grosso
    -0.44
    脚注の使い方
    -0.44
     kdy
    -0.43
    alogie
    -0.43
    POSITIVE LOGITS
     mourir
    0.65
     cherchés
    0.62
     băr
    0.55
     colorés
    0.55
     étrangères
    0.54
     titolata
    0.54
     vérit
    0.54
     negru
    0.54
     bidra
    0.54
     détru
    0.52
    Activations Density 0.001%

    No Known Activations