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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15554
    Prev
    Next
    INDEX
    Explanations

    references to the process of removing or resetting data or states

    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
    出版年
    -0.73
     مرئيه
    -0.62
    #+#
    -0.57
    atguigu
    -0.56
    зулта
    -0.56
     parete
    -0.55
    </thead>
    -0.52
     voisins
    -0.52
     contemporain
    -0.51
    glTexCoord
    -0.50
    POSITIVE LOGITS
     cleared
    2.38
     clearing
    2.38
    clearing
    2.13
    cleared
    2.11
     Clearing
    2.06
    Clearing
    2.00
     clears
    1.70
    Cleared
    1.56
     Clears
    1.01
    Lähteet
    0.74
    Activations Density 0.001%

    No Known Activations