© 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. 9626
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'd' at the beginning of a word

    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
    MENAFN
    -0.72
    ydın
    -0.60
    āya
    -0.60
    AVIS
    -0.60
    aden
    -0.59
    direktor
    -0.59
    hyrchwyd
    -0.57
    portlet
    -0.56
    σθαι
    -0.55
     aapt
    -0.54
    POSITIVE LOGITS
    スタル
    0.54
    ContentAsync
    0.54
    CodeAnalysis
    0.46
     vergangenen
    0.44
    ImageContext
    0.44
    Buenas
    0.44
    Parcelize
    0.43
    Collegamenti
    0.42
    phant
    0.42
     felipe
    0.42
    Activations Density 0.003%

    No Known Activations