© 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. 4694
    Prev
    Next
    INDEX
    Explanations

    Sentence fragments

    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
     Roskov
    -0.75
    Chham
    -0.67
     ―――――
    -0.66
    ImageContext
    -0.65
    $.
    -0.65
     stället
    -0.65
    Personendaten
    -0.65
     Мексичка
    -0.63
     againſt
    -0.63
    Архівовано
    -0.61
    POSITIVE LOGITS
     estimés
    0.58
    Especially
    0.56
    ful
    0.50
     Especially
    0.50
     especially
    0.49
     critical
    0.48
     Italijani
    0.47
     Indeed
    0.47
     particular
    0.46
    Indeed
    0.45
    Activations Density 0.009%

    No Known Activations