© 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
    2. Gemma-2-2B
    3. 2-RES-MATRYOSHKA-DC
    4. 6126
    Prev
    Next
    INDEX
    Explanations

    specific punctuation pattern involving closing braces and semicolons

    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
     nationaux
    -0.75
     auroit
    -0.73
     africains
    -0.72
     avoient
    -0.69
     devenus
    -0.69
     médicaux
    -0.69
     Philist
    -0.68
     Labyrinth
    -0.68
     feroit
    -0.68
    AFX
    -0.67
    POSITIVE LOGITS
    };
    
    1.63
    };
    1.59
     };
    
    1.57
     };
    1.53
    '};
    1.45
    "]:
    1.36
    '):
    
    1.35
    }};
    1.34
    ()};
    1.34
    ']):
    1.31
    Activations Density 0.185%

    No Known Activations