© 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. 5827
    Prev
    Next
    INDEX
    Explanations

    references to legal or political testimony, scandal, or corruption allegations

    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
     purpoſe
    -1.25
     myſelf
    -1.13
     houſe
    -1.13
     ſtate
    -1.09
     fubject
    -1.09
     pleaſure
    -1.09
     Houſe
    -1.07
     ſtre
    -1.05
     ſmall
    -1.05
     semelh
    -1.04
    POSITIVE LOGITS
     pra
    0.68
     em
    0.65
    ão
    0.64
     Brazil
    0.63
     Brazilian
    0.63
     Brasil
    0.62
    </i>
    0.60
    Brazilian
    0.60
     Janeiro
    0.59
     Tr
    0.58
    Activations Density 0.696%

    No Known Activations