© 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. 440
    Prev
    Next
    INDEX
    Explanations

    error messages or issues related to software or system failures

    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
     transfieras
    -0.61
     تضيفلها
    -0.60
     autorytatywna
    -0.59
    ographiques
    -0.57
    🏻
    -0.57
    nestjs
    -0.57
     strdup
    -0.56
     ListTile
    -0.55
    mybatisplus
    -0.55
     weakened
    -0.54
    POSITIVE LOGITS
     error
    4.56
     Error
    4.03
    error
    3.94
    Error
    3.66
     errors
    3.52
     ERROR
    3.25
     Errors
    3.23
    errors
    2.84
    Errors
    2.84
    ERROR
    2.83
    Activations Density 0.820%

    No Known Activations