© 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. 3697
    Prev
    Next
    INDEX
    Explanations

    references to the geometric concept of a sphere or spheres

    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
     ball
    -0.63
    ball
    -0.62
    MemoryWarning
    -0.59
     tiết
    -0.57
    沿革
    -0.56
     Goodwin
    -0.55
     against
    -0.54
    st
    -0.54
    бол
    -0.53
     spol
    -0.53
    POSITIVE LOGITS
     spheres
    2.89
     sphere
    2.84
    sphere
    2.75
     Sphere
    2.70
    spheres
    2.53
    pheres
    2.50
    Sphere
    2.28
     esfera
    1.80
    phere
    1.77
     esferas
    1.62
    Activations Density 0.008%

    No Known Activations