© 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. 3137
    Prev
    Next
    INDEX
    Explanations

    references to mathematical proofs and concepts related to algebraic geometry and cohomology

    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
    apunov
    -0.82
    richTextPanel
    -0.70
    rungsseite
    -0.56
    IBAction
    -0.56
    awaiter
    -0.56
    eqnarray
    -0.51
    esgue
    -0.51
     hereafter
    -0.49
    detectChanges
    -0.49
    DockStyle
    -0.49
    POSITIVE LOGITS
    WindowConstants
    0.64
    enumi
    0.62
    TypedDataSet
    0.58
     pylori
    0.57
     Palgrave
    0.56
    thâu
    0.54
     GoogleFonts
    0.53
    XmlEnum
    0.53
     Ceramby
    0.52
    اعده
    0.52
    Activations Density 1.787%

    No Known Activations