© 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. 98064
    Prev
    Next
    INDEX
    Explanations

    bring

    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
     autorytatywna
    -0.67
     nakalista
    -0.64
    ViewFeatures
    -0.64
    aspectj
    -0.63
     together
    -0.61
    |')
    -0.60
    }{*}{
    -0.59
    ChildScrollView
    -0.59
     referenties
    -0.59
    InjectAttribute
    -0.59
    POSITIVE LOGITS
     to
    0.66
     spéciaux
    0.52
     ultimi
    0.52
     vítimas
    0.51
     telinga
    0.51
     estudantes
    0.50
    reportWebVitals
    0.50
     visiteurs
    0.50
     (!_
    0.49
     investigadores
    0.48
    Activations Density 0.002%

    No Known Activations