© 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. 5217
    Prev
    Next
    INDEX
    Explanations

    references to cursor positions within code or data structures

    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
     autorytatywna
    -0.65
     protoimpl
    -0.58
    WebVitals
    -0.58
     quadro
    -0.55
    OrWhiteSpace
    -0.54
    CardHeader
    -0.53
     crom
    -0.52
    Seb
    -0.51
     transfieras
    -0.51
    StylePriority
    -0.51
    POSITIVE LOGITS
     cursor
    3.41
    cursor
    3.06
    Cursor
    3.00
     Cursor
    2.91
    CURSOR
    2.13
     curs
    1.95
    ursor
    1.83
    cursors
    1.78
    Cursors
    1.73
    setCursor
    1.63
    Activations Density 0.005%

    No Known Activations