© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92485
    Prev
    Next
    INDEX
    Explanations

    shore

    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
    ingly
    -0.61
     so
    -0.60
     “
    -0.60
     car
    -0.59
     "
    -0.57
     an
    -0.56
     par
    -0.55
    ighting
    -0.55
     (
    -0.54
     a
    -0.54
    POSITIVE LOGITS
     Persians
    1.03
     Shakspeare
    0.99
     Agamemnon
    0.98
     Assyrian
    0.98
     Athenian
    0.96
     Económica
    0.96
     Theſe
    0.94
     Athenians
    0.94
     Shaksp
    0.93
     ſeveral
    0.93
    Activations Density 1.550%

    No Known Activations