© 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. 3243
    Prev
    Next
    INDEX
    Explanations

    references to core components of Python or Java code, such as modules or packages

    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
    ;#
    -0.48
    +#+#
    -0.47
    }}{(
    -0.47
    EditPart
    -0.47
    ParseTree
    -0.46
    valho
    -0.45
     compareTo
    -0.44
    ämän
    -0.43
    ArrowToggle
    -0.43
    jsonPath
    -0.43
    POSITIVE LOGITS
    core
    2.34
    CORE
    1.25
    cores
    1.01
    cored
    0.87
    Core
    0.85
    coring
    0.82
     متعلقه
    0.73
     score
    0.72
     Cæsar
    0.71
     Jefus
    0.71
    Activations Density 0.007%

    No Known Activations