© 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. 20-CLT-HP
    7. 72368
    Prev
    Next
    INDEX
    Explanations

    just/merely

    np_max-act-logits · 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
    because
    -0.82
    Because
    -0.81
     Because
    -0.74
     كومونز
    -0.73
     للمعارف
    -0.71
     because
    -0.68
    karena
    -0.65
     BECAUSE
    -0.65
     porque
    -0.63
     kerana
    -0.62
    POSITIVE LOGITS
     just
    1.57
     simply
    1.34
    just
    1.23
     juste
    1.12
     JUST
    1.11
     Just
    1.10
     merely
    1.08
    Just
    1.07
    simply
    1.02
    JUST
    0.96
    Activations Density 0.000%

    No Known Activations