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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4245
    Prev
    Next
    INDEX
    Explanations

    passages related to clarifying or explaining complex scientific or technical issues

    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
    <tbody>
    -0.56
    <thead>
    -0.56
    bola
    -0.53
    Pautan
    -0.51
     wedi
    -0.50
    ívar
    -0.50
    phys
    -0.50
    <eos>
    -0.48
     ببر
    -0.48
    Vari
    -0.48
    POSITIVE LOGITS
     clarify
    2.70
     clarification
    2.50
     clarifying
    2.48
     clarified
    2.33
     Clar
    2.28
     clarifies
    2.17
    clar
    2.02
    Clar
    1.98
     clar
    1.85
     CLAR
    1.62
    Activations Density 0.007%

    No Known Activations