© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5767
    Prev
    Next
    INDEX
    Explanations

    references to specific scan procedures or measurement techniques

    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
     bench
    -0.62
    olah
    -0.57
    ⤹
    -0.57
    lierten
    -0.55
    assioned
    -0.55
     pâte
    -0.54
     conclusiones
    -0.54
    ENIX
    -0.54
     mcqueen
    -0.54
    PyObject
    -0.52
    POSITIVE LOGITS
     scan
    3.25
     scans
    2.88
    scan
    2.86
     Scan
    2.83
     scanning
    2.83
    Scan
    2.73
     scanned
    2.67
     SCAN
    2.55
    scanning
    2.50
     Scanning
    2.44
    Activations Density 0.024%

    No Known Activations