© 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. 489
    Prev
    Next
    INDEX
    Explanations

    United

    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
    RegressionTest
    -0.84
    UnusedPrivate
    -0.68
     تضيفلها
    -0.60
     Saltar
    -0.59
     Numerade
    -0.58
    Хро
    -0.57
    InjectAttribute
    -0.57
     Савезне
    -0.56
    IsMutable
    -0.55
    曖昧さ回避
    -0.54
    POSITIVE LOGITS
    ollectionView
    0.47
    ensement
    0.45
    ibald
    0.45
    rabble
    0.44
     DataLoader
    0.43
    Przypisy
    0.42
    chappement
    0.42
     Ober
    0.42
     Sidebar
    0.41
    restes
    0.41
    Activations Density 0.000%

    No Known Activations