© 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. 12761
    Prev
    Next
    INDEX
    Explanations

    specific dates and personal references in communication

    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
     susun
    -0.46
     sva
    -0.46
     but
    -0.42
     each
    -0.41
    命的
    -0.41
    鞠
    -0.41
    下一
    -0.40
    └──
    -0.40
    .*")]
    -0.40
     annul
    -0.40
    POSITIVE LOGITS
    GEBURTSDATUM
    0.77
     kasarigan
    0.71
    GEBURTS
    0.69
    ArrowToggle
    0.66
    出版年
    0.65
    MemoryWarning
    0.65
     Anſ
    0.64
     JpaRepository
    0.64
     otomatig
    0.63
    Referencie
    0.63
    Activations Density 0.012%

    No Known Activations