© 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. 93972
    Prev
    Next
    INDEX
    Explanations

    Code and technical documents

    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
     Públicas
    -0.63
     Democrá
    -0.58
    ypep
    -0.58
     hoarding
    -0.57
    ilibr
    -0.57
     téc
    -0.55
    protoimpl
    -0.55
     Técnica
    -0.55
    OOTDTY
    -0.55
     sexuelle
    -0.55
    POSITIVE LOGITS
     protoimpl
    0.59
    viewDidLoad
    0.58
    GEBURTSDATUM
    0.57
    ghest
    0.55
    DoubleQuotes
    0.51
    kháu
    0.51
    ʁ
    0.49
    Хьажоргаш
    0.49
     ancient
    0.47
    تقاوى
    0.47
    Activations Density 1.499%

    No Known Activations