© 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. 1-RES-MATRYOSHKA-DC
    7. 12
    Prev
    Next
    INDEX
    Explanations

    HTML tag attribute identifiers

    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
    }));
    -0.59
    __':
    -0.57
     nicio
    -0.57
    >';
    -0.56
     '-';
    -0.56
    )");
    -0.56
    ]').
    -0.55
    )";
    -0.54
     '.';
    -0.53
    ('');
    -0.52
    POSITIVE LOGITS
     name
    4.44
    name
    3.94
     Name
    3.91
    Name
    3.70
     NAME
    3.56
     names
    3.47
    NAME
    3.34
     Names
    3.06
    names
    2.92
     Namen
    2.89
    Activations Density 0.886%

    No Known Activations