© 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
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12180
    Prev
    Next
    INDEX
    Explanations

    Names and data

    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
     familières
    -0.56
     Cot
    -0.44
     BUN
    -0.44
     canopy
    -0.41
     Bun
    -0.41
    CopyWith
    -0.40
     ponytail
    -0.39
     головой
    -0.39
    BUN
    -0.39
     Robin
    -0.38
    POSITIVE LOGITS
    aarrggbb
    0.85
     autorytatywna
    0.80
     kaynağından
    0.73
    참고
    0.71
     createSlice
    0.68
    phosa
    0.67
     الحره
    0.66
    جوايز
    0.66
     MainAxisSize
    0.66
    
    0.66
    Activations Density 0.033%

    No Known Activations