© 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. 6440
    Prev
    Next
    INDEX
    Explanations

    references to specific code components or variable names

    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
    Obrázky
    -0.94
    DebuggerNonUser
    -0.77
    makeConstraints
    -0.75
    forChild
    -0.75
     jadx
    -0.73
    RegistryLite
    -0.72
     Chwiliwch
    -0.72
    abetes
    -0.71
    forRoot
    -0.70
    labelledby
    -0.70
    POSITIVE LOGITS
    gl
    2.97
    GL
    2.70
     GL
    2.19
     gl
    2.16
    Gl
    1.77
     Gl
    1.63
    gle
    1.14
    GLE
    1.10
    gli
    1.05
    GLI
    1.01
    Activations Density 0.034%

    No Known Activations