© 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. 3293
    Prev
    Next
    INDEX
    Explanations

    the presence of specific mathematical variables related to partial derivatives and functions in the context of advanced calculus or mathematical analysis

    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
    penup
    -0.63
     Diallo
    -0.57
    Gön
    -0.57
    MockMvc
    -0.56
    ivis
    -0.56
    BeginContext
    -0.53
     Survivors
    -0.53
    XmlNode
    -0.53
     Freire
    -0.52
    [--
    -0.52
    POSITIVE LOGITS
    var
    1.70
     var
    1.70
    VAR
    1.59
     Var
    1.54
    Var
    1.52
     VAR
    1.39
    varu
    0.83
    vara
    0.83
    vars
    0.82
    varna
    0.79
    Activations Density 0.040%

    No Known Activations