© 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. 4-CLT-HP
    7. 762
    Prev
    Next
    INDEX
    Explanations

    think

    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
     thinking
    -0.61
     knowing
    -0.54
     pensando
    -0.50
    ოს
    -0.48
     believing
    -0.48
    Knowing
    -0.47
     étant
    -0.47
     realizing
    -0.47
    thinking
    -0.46
     muut
    -0.45
    POSITIVE LOGITS
     propOrder
    0.90
    expandindo
    0.87
     you
    0.87
     there
    0.82
     that
    0.82
    SourceChecksum
    0.79
    AddWithValue
    0.79
     they
    0.78
     "
    0.78
    MigrationBuilder
    0.76
    Activations Density 0.003%

    No Known Activations