© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-RES-MATRYOSHKA-DC
    7. 1448
    Prev
    Next
    INDEX
    Explanations

    math and code snippets

    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
    Negative Logits
    Filmografie
    -0.77
    hmigung
    -0.56
     Efq
    -0.56
    StateToProps
    -0.54
    getDoctrine
    -0.54
    ❮
    -0.53
    naked
    -0.53
    ötet
    -0.53
    ToUpdate
    -0.52
    Naissance
    -0.51
    POSITIVE LOGITS
     ABC
    0.86
    abc
    0.81
     abc
    0.81
    ABCDEF
    0.78
    ABC
    0.75
    ABCD
    0.69
    xyz
    0.68
     ABCD
    0.67
    abcd
    0.66
    XYZ
    0.66
    Activations Density 1.154%

    No Known Activations