© 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. 0-CLT-HP
    7. 38630
    Prev
    Next
    INDEX
    Explanations

    Atlantic

    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
     Atlantic
    -2.38
    Atlantic
    -2.17
     atlantic
    -1.97
     ATLANTIC
    -1.84
    atlantic
    -1.44
     Atlántico
    -1.09
     Atlan
    -1.05
     تضيفلها
    -0.85
    Atlan
    -0.81
    ATL
    -0.80
    POSITIVE LOGITS
    us
    0.50
    an
    0.49
    a
    0.47
     sol
    0.44
    oq
    0.42
    as
    0.42
     City
    0.41
    ặc
    0.41
    o
    0.41
     Johansson
    0.41
    Activations Density 0.053%

    No Known Activations