© 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. 6-RES-MATRYOSHKA-DC
    7. 987
    Prev
    Next
    INDEX
    Explanations

    the word "avoid," sometimes along with nearby words that might indicate something negative.

    oai_token-act-pair · gemini-2.0-flash
    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
     publiques
    -0.78
    AccessorTable
    -0.72
    thenReturn
    -0.63
    bodyParser
    -0.62
     perubahan
    -0.61
     cambiado
    -0.61
    ững
    -0.60
     credentials
    -0.60
     MaterialApp
    -0.60
    CHL
    -0.60
    POSITIVE LOGITS
    avoid
    1.81
     avoid
    1.75
     Avoid
    1.71
    Avoid
    1.68
     avoiding
    1.68
     avoided
    1.66
     AVOID
    1.63
     Avoiding
    1.58
     avoids
    1.57
     avoidance
    1.56
    Activations Density 0.562%

    No Known Activations