© 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. 0-RES-MATRYOSHKA-DC
    7. 11316
    Prev
    Next
    INDEX
    Explanations

    references to avoidance behaviors or concepts related to avoiding negative consequences

    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
    umet
    -0.54
    ux
    -0.51
    nico
    -0.50
     muun
    -0.50
     McGu
    -0.48
     הפר
    -0.47
    yak
    -0.47
    Originally
    -0.47
    ragan
    -0.46
    冠
    -0.46
    POSITIVE LOGITS
    RenderAtEndOf
    0.82
     illustrative
    0.80
     */;
    0.79
     nahilalakip
    0.78
     myſelf
    0.76
     Serbie
    0.75
    spi
    0.75
     USPS
    0.75
     Савезне
    0.75
    CppMethod
    0.73
    Activations Density 0.070%

    No Known Activations