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. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16191
    Prev
    Next
    INDEX
    Explanations

    places denoting a paragraph break or the end of a clause that also coincide with an opinion being offered

    oai_token-act-pair · gemini-2.0-flash

    newline characters followed by a space.

    np_token-act-pair-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_16/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
     )}
    -0.58
     ).
    -0.57
     }));
    -0.54
     )
    -0.54
     }],
    -0.53
     }).
    -0.52
     '))
    -0.49
     ">
    -0.48
     });
    -0.48
     te
    -0.47
    POSITIVE LOGITS
    DockStyle
    0.94
     itſelf
    0.88
     Monfieur
    0.82
     Efq
    0.80
     ſhe
    0.77
     myſelf
    0.76
     pleaſure
    0.74
     Jefus
    0.72
     Anſ
    0.72
     Shakspeare
    0.71
    Activations Density 1.174%

    No Known Activations