© 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. 7271
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a target or goal

    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
    makeText
    -0.74
    ]--;
    -0.63
     Numerade
    -0.63
     للمعارف
    -0.63
    %");
    -0.63
    ().__
    -0.61
    IUrlHelper
    -0.61
    🤣🤣
    -0.60
    riwal
    -0.60
    ẻo
    -0.60
    POSITIVE LOGITS
     upto
    0.95
    Até
    0.82
    upto
    0.82
     hasta
    0.77
     Até
    0.72
     עד
    0.71
    Hasta
    0.71
     até
    0.69
     jusqu
    0.68
    hasta
    0.67
    Activations Density 0.048%

    No Known Activations