© 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. 42538
    Prev
    Next
    INDEX
    Explanations

    searching

    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
     chasing
    -1.04
    PerformLayout
    -0.88
    Searching
    -0.83
     searching
    -0.81
     pursuing
    -0.81
     waiting
    -0.80
    searching
    -0.80
    waiting
    -0.78
    trying
    -0.77
    seeking
    -0.77
    POSITIVE LOGITS
     down
    0.58
    álen
    0.49
     up
    0.49
    äfts
    0.49
     Leger
    0.49
    alai
    0.48
    qai
    0.47
     means
    0.47
     for
    0.47
     bout
    0.46
    Activations Density 0.106%

    No Known Activations