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. 2-GEMMASCOPE-TRANSCODER-16K
    4. 14145
    Prev
    Next
    INDEX
    Explanations

    words related to Italian geography, politics and business

    oai_token-act-pair · gemini-2.0-flash

    Regional abbreviations/names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_2/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     V
    -0.53
     v
    -0.49
     or
    -0.48
    みに
    -0.48
    mdp
    -0.48
    !
    -0.47
     qu
    -0.46
     Do
    -0.46
     elements
    -0.46
     Can
    -0.46
    POSITIVE LOGITS
    RetentionPolicy
    0.77
     Pythagoras
    0.76
     препратки
    0.74
    aarrggbb
    0.72
     Shakspeare
    0.72
     ventri
    0.71
     Byzantium
    0.69
     ་་
    0.68
     contextLoads
    0.68
    riwal
    0.68
    Activations Density 1.816%

    No Known Activations