© 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. 23566
    Prev
    Next
    INDEX
    Explanations

    instances of the word "then."

    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
     (
    -0.57
     spørs
    -0.55
     
    -0.55
     The
    -0.53
     A
    -0.49
     Min
    -0.49
    Session
    -0.45
     vhodné
    -0.44
    S
    -0.43
     prøve
    -0.43
    POSITIVE LOGITS
    StructEnd
    1.11
    IUrlHelper
    1.08
    principalColumn
    1.00
     дописавши
    0.96
     NSCoder
    0.93
    etheless
    0.92
     ویکی‌پدی
    0.92
    ScopeManager
    0.90
     Majefty
    0.90
     iſt
    0.90
    Activations Density 0.023%

    No Known Activations