© 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. 5844
    Prev
    Next
    INDEX
    Explanations

    actions related to preventing or steering clear of something

    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
     Catt
    -0.71
    AccessorTable
    -0.68
     незавершена
    -0.65
    Datuak
    -0.64
    stateProvider
    -0.63
    rspec
    -0.62
     kasarigan
    -0.62
    Enllaces
    -0.57
    transQ
    -0.56
    ReusableCell
    -0.56
    POSITIVE LOGITS
     avoid
    2.69
    avoid
    2.59
     Avoid
    2.48
     avoided
    2.47
    Avoid
    2.47
     avoiding
    2.47
     avoids
    2.42
     AVOID
    2.28
     avoidance
    2.23
     Avoiding
    2.20
    Activations Density 0.015%

    No Known Activations