© 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. 3-RES-MATRYOSHKA-DC
    7. 1793
    Prev
    Next
    INDEX
    Explanations

    the word "physical" and seemingly related words even when misspelled ("Physique")

    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
     geng
    -0.68
     שוליים
    -0.67
    ItemBackground
    -0.65
    новништво
    -0.63
     utafitiHapana
    -0.63
     Rev
    -0.62
    enterOuterAlt
    -0.61
    eterminate
    -0.61
     invokingState
    -0.61
    PreferredItem
    -0.60
    POSITIVE LOGITS
     physical
    2.77
     Physical
    2.73
    Physical
    2.66
    physical
    2.61
    Phys
    2.59
    phys
    2.56
     Phys
    2.50
     physically
    2.50
     PHYSICAL
    2.42
     phys
    2.41
    Activations Density 0.155%

    No Known Activations