© 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. 6024
    Prev
    Next
    INDEX
    Explanations

    references to specific formatted output or log messages related to system calls and debugging information

    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
    WriteLiteral
    -0.58
    ικής
    -0.54
    hattan
    -0.53
     Derfor
    -0.47
    avra
    -0.46
    therefore
    -0.44
     Benedict
    -0.44
    udd
    -0.44
    TargetException
    -0.44
    Impossible
    -0.43
    POSITIVE LOGITS
     betweenstory
    0.91
    MigrationBuilder
    0.79
     JpaRepository
    0.78
    abestanden
    0.73
    ViewFeatures
    0.72
    oredCriteria
    0.71
     propOrder
    0.71
    ActionMode
    0.67
     définiti
    0.67
     Walkover
    0.66
    Activations Density 0.152%

    No Known Activations