© 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. 2-RES-MATRYOSHKA-DC
    7. 7242
    Prev
    Next
    INDEX
    Explanations

    mentions of material being positioned or placed

    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
     location
    -1.13
    location
    -0.94
     locations
    -0.94
     Location
    -0.92
    Location
    -0.88
     Locations
    -0.81
     LOCATION
    -0.72
    Locations
    -0.71
     propOrder
    -0.68
     spot
    -0.65
    POSITIVE LOGITS
     located
    2.19
     situated
    1.86
     Located
    1.75
    Located
    1.62
    located
    1.56
     situé
    1.50
     ubicado
    1.46
     située
    1.37
     situés
    1.37
     Situated
    1.36
    Activations Density 0.039%

    No Known Activations