© 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. 40500
    Prev
    Next
    INDEX
    Explanations

    explosions or advancement

    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
     progress
    -1.10
    finally
    -1.03
     finally
    -0.98
     Finally
    -0.91
     наконец
    -0.88
     Progress
    -0.84
     established
    -0.81
     endlich
    -0.81
    Finally
    -0.78
    progress
    -0.77
    POSITIVE LOGITS
    MessageOf
    0.53
    RegressionTest
    0.51
     weekdays
    0.50
     localObject
    0.49
     zamanda
    0.45
    .
    0.44
    memcpy
    0.44
    migrationBuilder
    0.43
     unharmed
    0.43
     by
    0.43
    Activations Density 0.068%

    No Known Activations