© 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. 97609
    Prev
    Next
    INDEX
    Explanations

    code

    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
     Савезне
    -1.08
     itſelf
    -0.80
     AssemblyTitle
    -0.79
     GenerationType
    -0.78
     pleaſure
    -0.75
     againſt
    -0.74
     Eſ
    -0.73
     ſeveral
    -0.72
     becauſe
    -0.69
    protoimpl
    -0.69
    POSITIVE LOGITS
    
    0.51
    rovna
    0.48
    きり
    0.46
    Biographie
    0.46
     &___
    0.46
    маш
    0.42
     then
    0.41
     suddenly
    0.41
    braith
    0.40
     plads
    0.40
    Activations Density 0.275%

    No Known Activations