© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11216
    Prev
    Next
    INDEX
    Explanations

    references to specific quantum variables or operators in equations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tw
    -0.83
    ver
    -0.73
    lin
    -0.72
    ly
    -0.70
    insee
    -0.69
     Verne
    -0.67
     Hame
    -0.66
     Pickett
    -0.65
    Ver
    -0.64
    lla
    -0.64
    POSITIVE LOGITS
    Psi
    1.10
     Breen
    0.97
     PropTypes
    0.96
     Psi
    0.90
     Adri
    0.87
    oporosis
    0.87
     Brace
    0.85
    duate
    0.85
    orteur
    0.84
    ragt
    0.84
    Activations Density 0.010%

    No Known Activations