© 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. 73173
    Prev
    Next
    INDEX
    Explanations

    academic/technical snippets

    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
     kili
    -0.43
     referrerpolicy
    -0.43
    ler
    -0.41
     lipoprotein
    -0.40
    ciel
    -0.39
    nu
    -0.38
     fillings
    -0.38
    fil
    -0.38
     ve
    -0.38
    ServletConfig
    -0.37
    POSITIVE LOGITS
     textbook
    0.70
    GEBURTSDATUM
    0.67
    ControllerAdvice
    0.66
     leçon
    0.66
     createState
    0.65
    المناصب
    0.64
     nahilalakip
    0.63
     standardized
    0.62
     lesson
    0.62
     дописавши
    0.61
    Activations Density 0.001%

    No Known Activations