© 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. 5-CLT-HP
    7. 92335
    Prev
    Next
    INDEX
    Explanations

    Thinking or considering

    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
    yourself
    -0.45
    herself
    -0.44
     defaultstate
    -0.44
     Himself
    -0.43
     wiedzieć
    -0.38
    GeoNames
    -0.37
     herself
    -0.36
    himself
    -0.36
     rangs
    -0.35
     yourself
    -0.34
    POSITIVE LOGITS
    posedge
    0.75
    Yeet
    0.68
    はじめに
    0.68
    Rujukan
    0.68
     >=",
    0.66
     weighty
    0.66
     JFrame
    0.65
     surla
    0.63
    stark
    0.63
     the
    0.62
    Activations Density 0.002%

    No Known Activations