© 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. 12-RES-MATRYOSHKA-DC
    7. 2537
    Prev
    Next
    INDEX
    Explanations

    references to fields and categories in structured documents or reports

    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
     Cæsar
    -1.05
     Majefty
    -0.94
     himſelf
    -0.90
     Rossetti
    -0.90
     themſelves
    -0.88
     myſelf
    -0.88
     Monfieur
    -0.86
     Unger
    -0.84
     Tacitus
    -0.79
     Hogarth
    -0.79
    POSITIVE LOGITS
     Fields
    1.83
     fields
    1.77
     Field
    1.67
     getField
    1.66
     field
    1.64
    fields
    1.61
     FIELD
    1.60
    Fields
    1.59
     FIELDS
    1.55
    FIELDS
    1.50
    Activations Density 0.215%

    No Known Activations