© 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. 100
    Prev
    Next
    INDEX
    Explanations

    words associated with the position and dimensions of objects with respect to each other or to a frame of reference

    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
    PMailer
    -0.70
    CreateMap
    -0.69
     guste
    -0.68
    Vidite
    -0.68
     Krakowie
    -0.68
    %)$
    -0.67
    ethnicity
    -0.66
     chimique
    -0.65
    ModelSerializer
    -0.65
     Réponses
    -0.65
    POSITIVE LOGITS
     bottom
    1.04
    bottom
    1.04
     houſe
    0.98
     purpoſe
    0.92
     BOTTOM
    0.92
     Bottom
    0.90
    north
    0.90
     Houſe
    0.90
     ſtate
    0.88
     north
    0.85
    Activations Density 19.750%

    No Known Activations