Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12943
    Prev
    Next
    INDEX
    Explanations

    Col

    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
    Personendaten
    -0.58
     Idio
    -0.56
     colorless
    -0.52
    matitis
    -0.52
     Composition
    -0.51
    arial
    -0.51
    invokeLater
    -0.51
    AndEndTag
    -0.51
     Taro
    -0.51
     mété
    -0.50
    POSITIVE LOGITS
    DispatchToProps
    0.65
    
    0.62
    gemeester
    0.56
    UMBIA
    0.56
    ValueStyle
    0.54
    Legături
    0.51
    endphp
    0.51
    ennung
    0.51
    mybatisplus
    0.49
    Referințe
    0.47
    Activations Density 0.008%

    No Known Activations