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-RES-MATRYOSHKA-DC
    4. 10
    Prev
    Next
    INDEX
    Explanations

    references to styled or formatted text segments, specifically spans and HTML markup

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    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
    aggia
    -0.53
    LookAnd
    -0.53
    uteen
    -0.53
    (!__
    -0.50
     hő
    -0.50
    '&:
    -0.49
     åt
    -0.47
    copyWith
    -0.47
    VEY
    -0.47
     strictly
    -0.46
    POSITIVE LOGITS
     []:
    1.13
    </thead>
    1.05
    </table>
    0.93
    </blockquote>
    0.91
    发表于
    0.91
    </tfoot>
    0.89
    </tbody>
    0.88
    ‬‬
    0.88
    endphp
    0.88
    ագրություններ
    0.87
    Activations Density 3.381%

    No Known Activations