© 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. 9762
    Prev
    Next
    INDEX
    Explanations

    references to knights and related terms in various contexts

    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
     faudra
    -0.72
     MTC
    -0.71
     Nero
    -0.71
    odotus
    -0.70
    TextWatcher
    -0.70
     Esther
    -0.69
     Utica
    -0.69
    *~*~
    -0.69
     FAP
    -0.69
     Morton
    -0.68
    POSITIVE LOGITS
     Kn
    1.23
     kn
    1.21
    Kn
    1.20
     Knights
    1.19
     Knight
    1.15
    kn
    1.07
     Knud
    1.03
     KN
    1.02
     knight
    1.02
     KNIGHT
    1.00
    Activations Density 0.013%

    No Known Activations