© 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. 45047
    Prev
    Next
    INDEX
    Explanations

    exaggerated

    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
     goblet
    -0.77
    CppCodeGen
    -0.63
    idł
    -0.62
     exaggerated
    -0.61
     prisonniers
    -0.59
    äldrar
    -0.57
    vartis
    -0.57
     gou
    -0.55
     banques
    -0.53
    option
    -0.53
    POSITIVE LOGITS
     autorytatywna
    0.72
    تقاوى
    0.63
     betweenstory
    0.61
     ExecuteAsync
    0.61
    i
    0.56
    rungsseite
    0.55
     تضيفلها
    0.52
    Personendaten
    0.50
     pastic
    0.48
    afficheront
    0.48
    Activations Density 1.538%

    No Known Activations