© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45652
    Prev
    Next
    INDEX
    Explanations

    protein

    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
    ing
    -0.56
    by
    -0.52
    frame
    -0.50
    man
    -0.49
     
    -0.45
    und
    -0.45
      
    -0.44
    <strong>
    -0.44
    hiro
    -0.44
    mun
    -0.43
    POSITIVE LOGITS
    WithIOException
    1.63
    Personendaten
    1.38
    parsedMessage
    1.23
    AddTagHelper
    1.22
    AndEndTag
    1.20
    ValueStyle
    1.16
    __':
    
    1.15
    GEBURTSDATUM
    1.14
     CreateTagHelper
    1.13
     Мексичка
    1.12
    Activations Density 0.271%

    No Known Activations