© 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. 0-CLT-HP
    7. 97706
    Prev
    Next
    INDEX
    Explanations

    also, called

    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
     of
    -0.60
    orous
    -0.57
    ly
    -0.56
    ing
    -0.53
    ,
    -0.52
    to
    -0.51
    -
    -0.50
     in
    -0.50
    less
    -0.50
    of
    -0.49
    POSITIVE LOGITS
    GEBURTSDATUM
    1.25
     AssemblyCulture
    1.24
    ंदीखरीदारी
    1.12
     cherchés
    1.07
    Personensuche
    1.05
    expandindo
    1.05
    AccessorTable
    1.03
     propOrder
    1.02
    InjectAttribute
    1.02
     تضيفلها
    1.02
    Activations Density 0.152%

    No Known Activations