© 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. 5818
    Prev
    Next
    INDEX
    Explanations

    instances of the differential operator used in calculus

    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
     GenerationType
    -0.69
     ffilm
    -0.59
    ExtendWith
    -0.54
     nahilalakip
    -0.51
    Geplaatst
    -0.50
    FromArgb
    -0.50
    SpringBootTest
    -0.49
    WindowConstants
    -0.49
    itext
    -0.49
     })}
    -0.49
    POSITIVE LOGITS
    dx
    0.90
     dx
    0.80
    riwal
    0.73
    ografija
    0.66
     Мексичка
    0.64
    GetAxis
    0.63
    bronn
    0.61
    ylem
    0.60
    toCharArray
    0.59
    rinfo
    0.59
    Activations Density 0.459%

    No Known Activations