© 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. 3-RES-MATRYOSHKA-DC
    7. 122
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to activate on a wide variety of contexts, including math formulas, code snippets, sexual content, and legal/medical information, but it is not clear what connects them

    oai_token-act-pair · gemini-2.0-flash
    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
    ])),
    -0.71
     jsPsych
    -0.69
    ()]);
    -0.60
     kaarangay
    -0.59
    }}},
    -0.58
    Autoritní
    -0.56
    )."
    -0.55
    )],
    -0.54
    ])).
    -0.54
     propOrder
    -0.54
    POSITIVE LOGITS
     تضيفلها
    0.95
    twimg
    0.88
     itself
    0.76
    basicConfig
    0.75
     saites
    0.75
    WithValue
    0.72
    StructEnd
    0.68
    üche
    0.65
     BoxFit
    0.64
    ddots
    0.63
    Activations Density 24.138%

    No Known Activations