© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45083
    Prev
    Next
    INDEX
    Explanations

    weekend

    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
     betweenstory
    -1.34
     للاسماء
    -1.34
     GenerationType
    -1.20
     تضيفلها
    -1.20
    RenderAtEndOf
    -1.16
    
    -1.15
     SwitchCompat
    -1.12
     propOrder
    -1.11
    انيف
    -1.10
     mergeFrom
    -1.06
    POSITIVE LOGITS
     of
    0.71
     in
    0.65
    ,
    0.49
     beyond
    0.45
     žem
    0.44
    .
    0.42
     ailleurs
    0.41
     retrou
    0.41
     épreuves
    0.41
     -
    0.38
    Activations Density 0.116%

    No Known Activations