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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74363
    Prev
    Next
    INDEX
    Explanations

    number 8

    np_max-act-logits · 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
    帖最后由
    -0.65
    
    -0.57
    发表于
    -0.57
    
    -0.57
    ":[{
    -0.57
    脚注の使い方
    -0.54
    ंदीखरीदारी
    -0.53
    RegistryLite
    -0.53
    UseVisualStyle
    -0.52
     <<<<<<<<<<<<<<
    -0.52
    POSITIVE LOGITS
    8
    0.71
     Eighth
    0.59
    ISSA
    0.52
     eighth
    0.51
     Eight
    0.50
     eight
    0.49
     باشیم
    0.49
    IRI
    0.49
    Eight
    0.49
     Eig
    0.49
    Activations Density 0.002%

    No Known Activations