© 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. 5968
    Prev
    Next
    INDEX
    Explanations

    the word "always" and its variations

    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
    er
    -0.94
    tagHelperRunner
    -0.94
    MACRO
    -0.77
    minX
    -0.76
     DVI
    -0.75
    ProcessEvent
    -0.72
    reportWebVitals
    -0.72
    ever
    -0.72
    Portale
    -0.72
     MACRO
    -0.72
    POSITIVE LOGITS
     Always
    0.94
     always
    0.93
    ALWAYS
    0.92
    Always
    0.91
    always
    0.89
     selalu
    0.88
     ALWAYS
    0.86
     siempre
    0.76
    alsh
    0.71
     altijd
    0.71
    Activations Density 0.036%

    No Known Activations