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. 20-CLT-HP
    4. 74330
    Prev
    Next
    INDEX
    Explanations

    for different languages

    np_max-act-logits · 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
     to
    -1.24
     of
    -1.12
    DataTo
    -0.63
     سكانية
    -0.61
    SpringBootTest
    -0.61
    verhältnisse
    -0.59
     الحره
    -0.59
    Brainz
    -0.57
    institution
    -0.56
     стаття
    -0.55
    POSITIVE LOGITS
     for
    0.65
     für
    0.60
     voor
    0.57
    for
    0.56
     для
    0.53
    für
    0.50
     jspb
    0.46
     עבור
    0.46
     تضيفلها
    0.45
     pentru
    0.45
    Activations Density 0.003%

    No Known Activations