© 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. 2-RES-MATRYOSHKA-DC
    7. 5448
    Prev
    Next
    INDEX
    Explanations

    references to eggs and egg-related 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
     Barlow
    -0.68
    cipar
    -0.66
    complexType
    -0.56
    UrlResolution
    -0.56
    ')")
    -0.55
    dide
    -0.53
     سكانية
    -0.52
    ManagedBean
    -0.52
     թվական
    -0.51
     Ström
    -0.51
    POSITIVE LOGITS
     egg
    3.52
     Egg
    3.30
     eggs
    3.19
    Egg
    3.13
    egg
    3.11
     Eggs
    3.00
     EGG
    2.75
    Eggs
    2.72
    eggs
    2.64
     œufs
    1.98
    Activations Density 0.006%

    No Known Activations