© 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. 6-RES-MATRYOSHKA-DC
    7. 144
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming syntax

    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
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -1.08
     mapStateToProps
    -1.04
    mapStateToProps
    -1.00
    AccessFile
    -0.97
     >=",
    -0.91
     تعدى
    -0.86
    abestanden
    -0.84
     BoxDecoration
    -0.83
     ControllerBase
    -0.82
     useRouter
    -0.82
    POSITIVE LOGITS
     E
    0.89
     EG
    0.83
     ECS
    0.80
    E
    0.80
     Eb
    0.80
     Esk
    0.77
     e
    0.75
     Eggs
    0.74
    EGL
    0.74
    Eggs
    0.73
    Activations Density 4.618%

    No Known Activations