© 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. 17541
    Prev
    Next
    INDEX
    Explanations

    references to noble individuals and titles

    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
    wn
    -0.66
     Francine
    -0.66
    >);
    -0.64
     trock
    -0.63
     dvo
    -0.63
    bnf
    -0.60
    n
    -0.60
     Martinez
    -0.60
     Healy
    -0.60
     Staates
    -0.59
    POSITIVE LOGITS
     Noble
    1.44
    Noble
    1.43
     Nobel
    1.28
     Nobles
    1.27
     nobles
    1.26
     noble
    1.22
    Nobel
    1.21
     nobility
    1.18
    noble
    1.10
     nobler
    1.07
    Activations Density 0.004%

    No Known Activations