© 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. 1-RES-MATRYOSHKA-DC
    7. 828
    Prev
    Next
    INDEX
    Explanations

    references to the concept of avoiding or reducing 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
     Sutherland
    -0.64
     dysfunction
    -0.56
     malfunction
    -0.55
     initComponents
    -0.54
    TagMode
    -0.52
     Exactos
    -0.51
    ero
    -0.50
     morte
    -0.50
     Dysfunction
    -0.50
    findOneAndUpdate
    -0.49
    POSITIVE LOGITS
     avoid
    3.38
    avoid
    3.28
     avoiding
    3.19
     avoided
    3.16
     Avoid
    3.11
    Avoid
    3.08
     avoidance
    3.02
     avoids
    3.02
     Avoiding
    2.91
     AVOID
    2.88
    Activations Density 0.494%

    No Known Activations