© 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
    2. Gemma-2-2B
    3. 2-RES-MATRYOSHKA-DC
    4. 6970
    Prev
    Next
    INDEX
    Explanations

    references to quantities or measurements

    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
    ImageContext
    -0.69
    WithIOException
    -0.68
     Wikimédia
    -0.68
    
    -0.68
    FailureListener
    -0.66
    rrggbb
    -0.66
    iterran
    -0.65
    km
    -0.65
     disambiguazione
    -0.65
    ArrowToggle
    -0.63
    POSITIVE LOGITS
     pounds
    2.16
     pound
    2.11
    pound
    1.80
     gallons
    1.55
    Pound
    1.55
     Pounds
    1.54
     Pound
    1.49
    pounds
    1.48
     gallon
    1.34
     ounces
    1.31
    Activations Density 0.115%

    No Known Activations