© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42469
    Prev
    Next
    INDEX
    Explanations

    ED

    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
    -0.97
    
    -0.80
    Rüyada
    -0.78
    ineno
    -0.76
    fulness
    -0.70
     isles
    -0.69
    queryInterface
    -0.69
    PreferredItem
    -0.68
    ⤹
    -0.65
    setVerticalGroup
    -0.64
    POSITIVE LOGITS
    oğlu
    0.47
    a
    0.41
     *
    0.37
    ogly
    0.36
     krig
    0.36
     szerint
    0.36
     igjen
    0.35
     PyTuple
    0.35
     lijn
    0.35
    ohjel
    0.34
    Activations Density 0.024%

    No Known Activations