© 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. 777
    Prev
    Next
    INDEX
    Explanations

    mentions of energy with units or math terms or physics formulas

    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
     circumcision
    -0.63
    ItemBackground
    -0.61
     Rousse
    -0.56
     Loa
    -0.55
     borra
    -0.55
     Estad
    -0.54
     Leit
    -0.54
    circum
    -0.54
    Ih
    -0.54
    steer
    -0.54
    POSITIVE LOGITS
     energy
    2.98
    energy
    2.67
     Energy
    2.66
    Energy
    2.56
     ENERGY
    2.55
     energies
    2.50
    ENERGY
    2.36
    energies
    2.20
     Energies
    2.19
     énergie
    2.05
    Activations Density 0.141%

    No Known Activations