© 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. 18-RES-MATRYOSHKA-DC
    7. 759
    Prev
    Next
    INDEX
    Explanations

    the word matrix in mathematical or technical contexts

    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/blocks.18.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amaño
    -0.54
    SourceChecksum
    -0.52
    grove
    -0.50
    optarg
    -0.49
     abandonné
    -0.48
    keur
    -0.47
     abbandon
    -0.46
    tagext
    -0.45
    haustible
    -0.44
    adog
    -0.44
    POSITIVE LOGITS
     matrix
    1.52
     Matrix
    1.43
     matrices
    1.35
    Matrix
    1.34
    matrix
    1.31
    矩阵
    1.24
     MATRIX
    1.23
     Matrices
    1.21
     matriz
    1.19
     matrice
    1.16
    Activations Density 1.765%

    No Known Activations