© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 31835
    Prev
    Next
    INDEX
    Explanations

    references to observers or measurements related to observer reliability

    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
    Negative Logits
     Piac
    -0.74
     Rockwell
    -0.70
     Huerta
    -0.70
     Eud
    -0.70
    PROPERTIES
    -0.69
     Efq
    -0.69
     liberi
    -0.68
    Occurrence
    -0.67
     Folsom
    -0.67
     Wap
    -0.65
    POSITIVE LOGITS
     observer
    1.24
    Observer
    1.23
    observer
    1.22
     Observer
    1.19
     observers
    1.16
    observers
    1.11
    Observers
    0.98
     Sek
    0.84
    AnchorTagHelper
    0.75
    reportError
    0.74
    Activations Density 0.002%

    No Known Activations