© 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. 91495
    Prev
    Next
    INDEX
    Explanations

    different

    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
     Мексичка
    -0.76
     onOptions
    -0.72
    RenderAtEndOf
    -0.71
     мәкал
    -0.68
     jury
    -0.64
     Paglinawan
    -0.63
    Personendaten
    -0.63
    Хьажоргаш
    -0.62
    enumi
    -0.62
    kuuta
    -0.62
    POSITIVE LOGITS
     and
    0.68
     âmes
    0.54
    ,
    0.48
    when
    0.46
    handling
    0.44
     larmes
    0.43
     fidèles
    0.42
     âgées
    0.42
     hiér
    0.42
    handle
    0.42
    Activations Density 0.004%

    No Known Activations