© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 294
    Prev
    Next
    INDEX
    Explanations

    mentions of colors used for materials or objects

    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
    __":
    -1.21
    __':
    -1.07
     propOrder
    -1.05
    makeConstraints
    -1.02
    __":
    -0.99
     الحره
    -0.97
    __':
    -0.92
     оригіналу
    -0.88
    Personendaten
    -0.88
    ″]
    -0.86
    POSITIVE LOGITS
     black
    1.67
    black
    1.67
     white
    1.59
    white
    1.59
    Black
    1.50
     Black
    1.45
     yellow
    1.44
     colored
    1.44
    BLACK
    1.43
    White
    1.41
    Activations Density 1.505%

    No Known Activations