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. 0-CLT-HP
    4. 40877
    Prev
    Next
    INDEX
    Explanations

    boxing

    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
    findpost
    -0.87
     boxing
    -0.76
     boxers
    -0.76
    ImageContext
    -0.76
     boxer
    -0.75
     ecto
    -0.73
    хьтан
    -0.73
    adpleegd
    -0.71
     themſelves
    -0.69
    TemporalType
    -0.69
    POSITIVE LOGITS
     lí
    0.49
    ska
    0.49
     Key
    0.47
    er
    0.45
     relevant
    0.45
    ERIC
    0.45
     gl
    0.45
    eri
    0.44
    eris
    0.44
    戴
    0.44
    Activations Density 1.841%

    No Known Activations