© 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. 4398
    Prev
    Next
    INDEX
    Explanations

    Binding language

    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
     disambiguazione
    -0.78
    ViewFeatures
    -0.71
    Portale
    -0.60
     initComponents
    -0.57
    
    -0.56
     OFDb
    -0.56
    IndentedString
    -0.54
    طلحات
    -0.54
    Portail
    -0.54
    IANGLES
    -0.53
    POSITIVE LOGITS
    üglich
    0.48
     vermelhas
    0.47
    withIdentifier
    0.47
     vora
    0.46
     leçon
    0.45
     Association
    0.45
     comigo
    0.45
     ervan
    0.45
     ↓,
    0.44
     rayures
    0.43
    Activations Density 0.009%

    No Known Activations