© 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. 26380
    Prev
    Next
    INDEX
    Explanations

    words related to capitalization styles in text

    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
    VIAF
    -0.70
     turística
    -0.59
     }}"></
    -0.59
     MRP
    -0.58
    StoreMessageInfo
    -0.57
    Susie
    -0.55
     defStyle
    -0.55
     IRQ
    -0.55
     @"";
    -0.55
     Trow
    -0.54
    POSITIVE LOGITS
    caps
    1.00
     CAPS
    0.88
     Cap
    0.84
    TagMode
    0.78
    CAPS
    0.77
    Caps
    0.77
    cap
    0.74
     caps
    0.71
    Cap
    0.69
     Caps
    0.68
    Activations Density 0.002%

    No Known Activations