© 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. 23330
    Prev
    Next
    INDEX
    Explanations

    variations of the word "hello."

    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
     VIAF
    -0.87
    VIAF
    -0.79
    AsUp
    -0.77
    valbard
    -0.67
    odziel
    -0.64
    렀
    -0.63
    .*")]
    -0.63
    WithIOException
    -0.63
     furent
    -0.62
    siąż
    -0.60
    POSITIVE LOGITS
    HELLO
    1.13
     hello
    1.02
     HELLO
    0.99
     Hello
    0.90
    hello
    0.88
    Hello
    0.81
     Merci
    0.81
     Scherer
    0.80
     Netto
    0.78
     Mons
    0.77
    Activations Density 0.005%

    No Known Activations