© 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. 6-RES-MATRYOSHKA-DC
    7. 1139
    Prev
    Next
    INDEX
    Explanations

    phrases involving a central location or axis

    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
    PreferredItem
    -0.86
    ècie
    -0.84
    :✨
    -0.83
    psack
    -0.69
     Hogarth
    -0.69
    sApp
    -0.66
    ainville
    -0.66
     boire
    -0.65
    Quebec
    -0.65
     Vietnamese
    -0.63
    POSITIVE LOGITS
     center
    1.79
     centre
    1.77
     centers
    1.73
     centres
    1.67
    center
    1.59
     Centers
    1.59
     Center
    1.58
     Centre
    1.53
    centre
    1.53
     CENTER
    1.51
    Activations Density 0.272%

    No Known Activations