© 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. 16835
    Prev
    Next
    INDEX
    Explanations

    phrases indicating necessity or obligation involving the word "one."

    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
    PerformLayout
    -0.98
     autorytatywna
    -0.70
    äsenti
    -0.66
    reportWebVitals
    -0.62
    ilosop
    -0.61
     AssemblyCulture
    -0.59
     expedi
    -0.59
    olut
    -0.59
    ędzie
    -0.59
    anaf
    -0.58
    POSITIVE LOGITS
     oneself
    1.03
     يتيمه
    0.90
    eseorang
    0.66
    MLLoader
    0.62
    Referències
    0.60
    ешься
    0.60
    ymce
    0.60
    Lugares
    0.60
     aig
    0.59
    QUIR
    0.58
    Activations Density 0.032%

    No Known Activations