© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 11213
    Prev
    Next
    INDEX
    Explanations

    the presence of specific geometric shapes representing circles in graphical data

    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
    findpost
    -0.88
     Circle
    -0.85
    UIControlState
    -0.67
    localctx
    -0.66
    Circle
    -0.66
    BufferException
    -0.65
    setVerticalGroup
    -0.63
    жидан
    -0.63
    ParallelGroup
    -0.61
     espont
    -0.61
    POSITIVE LOGITS
     circles
    2.41
    circles
    1.72
     Circles
    1.56
    Circles
    1.43
     círculos
    1.18
     rings
    0.75
    Personensuche
    0.72
     Kreise
    0.68
     spheres
    0.61
     dots
    0.58
    Activations Density 0.002%

    No Known Activations