© 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. 5875
    Prev
    Next
    INDEX
    Explanations

    mentions of the color black

    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
     red
    -0.79
     green
    -0.77
    green
    -0.74
    red
    -0.69
     pink
    -0.65
    reds
    -0.65
     blue
    -0.64
     Red
    -0.61
     RED
    -0.61
     GREEN
    -0.60
    POSITIVE LOGITS
     Black
    2.84
     black
    2.81
    Black
    2.78
    black
    2.66
     BLACK
    2.56
    BLACK
    2.47
     blacks
    2.02
    黑
    1.90
     zwarte
    1.87
     Blacks
    1.84
    Activations Density 0.030%

    No Known Activations