© 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. 14516
    Prev
    Next
    INDEX
    Explanations

    punctuation and conjunctions

    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
    gia
    -0.51
    askar
    -0.49
    RectangleBorder
    -0.46
     Zam
    -0.46
     clash
    -0.45
     Hunter
    -0.44
     WARRANTIES
    -0.44
    bacher
    -0.44
     ferroviaire
    -0.43
    cipitation
    -0.43
    POSITIVE LOGITS
    PreferredItem
    0.81
     NSCoder
    0.65
     betreft
    0.63
    OfYear
    0.62
    StructEnd
    0.62
    mappedBy
    0.60
    ις
    0.60
    بوابة
    0.59
     initComponents
    0.59
    ็จ
    0.59
    Activations Density 0.117%

    No Known Activations