© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15299
    Prev
    Next
    INDEX
    Explanations

    formatted HTML code snippets and specific terminating characters

    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
    ⓘ
    -0.79
    참고
    -0.72
     élevées
    -0.67
     complètes
    -0.63
     scattata
    -0.62
    titleMargin
    -0.62
    mnop
    -0.61
     réal
    -0.59
     lemonade
    -0.59
     religieux
    -0.59
    POSITIVE LOGITS
    )</
    3.08
    ]</
    1.13
    ).</
    1.08
    )*/
    0.79
    )}</
    0.73
     }}</
    0.70
    }</
    0.69
    }}</
    0.68
     సౌకర్య
    0.66
     }</
    0.65
    Activations Density 0.000%

    No Known Activations