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. 14158
    Prev
    Next
    INDEX
    Explanations

    mentions of ownership, specifically in the context of slavery

    oai_token-act-pair · gemini-2.0-flash

    owned

    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
     owned
    -1.61
     Owned
    -1.57
    owned
    -1.49
    Owned
    -1.29
     Ownership
    -1.14
     ownership
    -1.11
    ownership
    -1.09
     owning
    -0.98
    Ownership
    -0.98
     owns
    -0.92
    POSITIVE LOGITS
     arşivlendi
    0.64
    <bos>
    0.63
     })}
    0.59
    __*/
    0.55
    Демографія
    0.51
     تضيفلها
    0.50
    )*/
    0.50
    ]));
    
    0.49
    consulté
    0.49
    esez
    0.49
    Activations Density 0.876%

    No Known Activations