© 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. 0-RES-MATRYOSHKA-DC
    7. 11601
    Prev
    Next
    INDEX
    Explanations

    spatial arrangements of structured components

    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
     arrangement
    -1.10
     arrangements
    -1.02
     Arrangements
    -0.83
     Arrangement
    -0.75
    __":
    -0.68
    Arrangements
    -0.66
    __':
    -0.65
    arrangement
    -0.61
     organization
    -0.60
     preparations
    -0.59
    POSITIVE LOGITS
     arranged
    1.80
     Arranged
    1.52
    arranged
    1.26
     arranges
    1.00
    Arrange
    0.74
     Arrange
    0.69
     arranging
    0.68
    MigrationBuilder
    0.66
     arrange
    0.65
    AndEndTag
    0.62
    Activations Density 0.003%

    No Known Activations