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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11162
    Prev
    Next
    INDEX
    Explanations

    negative statements about political power

    oai_token-act-pair · gemini-2.0-flash

    ordinal terms

    np_token-act-pair-logits · gpt-4o-mini

    second

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/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
    })`
    -0.74
    )";
    
    -0.55
    }")
    
    -0.53
    )");
    
    -0.51
     Tense
    -0.49
     nôtre
    -0.49
    }]
    
    -0.49
    AndEndTag
    -0.48
    )]
    
    -0.48
    '):
    
    -0.47
    POSITIVE LOGITS
     second
    1.07
    second
    0.88
     Second
    0.78
     SECOND
    0.77
     third
    0.76
     secondary
    0.74
     seconde
    0.73
    SECOND
    0.72
    Second
    0.71
     segundo
    0.68
    Activations Density 1.732%

    No Known Activations