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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 3752
    Prev
    Next
    INDEX
    Explanations

    the

    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
     accurate
    -0.76
     accurately
    -0.71
    accurate
    -0.69
    Accurate
    -0.69
     Accurate
    -0.66
     correct
    -0.59
     correctly
    -0.57
     precise
    -0.56
     inaccurate
    -0.51
    正確
    -0.51
    POSITIVE LOGITS
    AnimationsModule
    1.07
    
    0.95
     ComVisible
    0.85
    AndEndTag
    0.84
    TagMode
    0.79
    findpost
    0.78
    IndentedString
    0.76
    出版年
    0.74
    躇
    0.71
     GenerationType
    0.70
    Activations Density 0.008%

    No Known Activations