© 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. 72865
    Prev
    Next
    INDEX
    Explanations

    substitution and replacement

    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
     change
    -1.66
     changing
    -1.62
     changed
    -1.61
     Change
    -1.47
    change
    -1.42
    Change
    -1.41
     swap
    -1.40
     CHANGE
    -1.40
    changing
    -1.39
     changes
    -1.38
    POSITIVE LOGITS
    homonymie
    0.51
    rdı
    0.51
     out
    0.49
     poiv
    0.49
    cocc
    0.48
     pacchetto
    0.48
     pâtes
    0.44
     battre
    0.43
    fury
    0.43
     nemico
    0.43
    Activations Density 0.002%

    No Known Activations