© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3053
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    сылкі
    -0.73
     "..\..\
    -0.73
     ddelweddau
    -0.71
    Хьажоргаш
    -0.71
    RegressionTest
    -0.69
    adaptiveStyles
    -0.69
    Portale
    -0.63
    Personensuche
    -0.63
     Baillargeon
    -0.62
    اریخ
    -0.62
    POSITIVE LOGITS
     that
    0.74
     there
    0.65
     so
    0.63
     they
    0.63
     introducing
    0.60
     providing
    0.56
     choosing
    0.55
     the
    0.55
     selecting
    0.54
     what
    0.54
    Activations Density 0.021%

    No Known Activations