© 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. 6332
    Prev
    Next
    INDEX
    Explanations

    patterns involving code structure or syntax elements such as braces, brackets, or similar delimiters

    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
    migrationBuilder
    -0.55
     محفوظة
    -0.52
     ]];
    -0.52
    WithIdentifier
    -0.50
    armed
    -0.49
     CommandType
    -0.48
    cilis
    -0.48
     arm
    -0.48
     ')
    -0.47
    Gris
    -0.47
    POSITIVE LOGITS
    存于互联网档案馆
    0.67
    SourceChecksum
    0.65
     Administrativna
    0.63
     生命周期
    0.61
     Constitucional
    0.59
     abstrait
    0.58
     disambiguazione
    0.58
    lazione
    0.58
     Infórmanos
    0.58
     subgoals
    0.58
    Activations Density 0.084%

    No Known Activations