© 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. 4233
    Prev
    Next
    INDEX
    Explanations

    references to the color orange

    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
    CONSIN
    -0.68
     black
    -0.65
    black
    -0.63
     utafitiHapana
    -0.63
     Mehl
    -0.62
     Morm
    -0.62
    corer
    -0.59
     zwarte
    -0.59
    Tazama
    -0.59
     defStyle
    -0.59
    POSITIVE LOGITS
     Orange
    3.31
    Orange
    3.06
     orange
    2.94
     ORANGE
    2.91
    orange
    2.64
    ORANGE
    2.44
     oranges
    2.25
     naranja
    2.05
     Oranges
    2.05
     laranja
    1.80
    Activations Density 0.003%

    No Known Activations