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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 2-GEMMASCOPE-TRANSCODER-16K
    4. 14304
    Prev
    Next
    INDEX
    Explanations

    certain prepositions and nouns associated with taking initiative or negative effects on privacy

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_2/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.88
     lenker
    -0.62
     HasFactory
    -0.62
     cuire
    -0.55
    OleDb
    -0.54
     incomplète
    -0.54
     عن
    -0.53
    RTDA
    -0.53
    ómicos
    -0.52
     '\\;'
    -0.52
    POSITIVE LOGITS
    ReusableCell
    0.69
    BeginContext
    0.57
     الاطلاع
    0.56
    ittäin
    0.55
     الرياضيه
    0.54
     actionMode
    0.52
    )=>{
    
    0.51
    المشاركات
    0.50
    __);
    0.50
    ).)
    0.50
    Activations Density 1.195%

    No Known Activations