© 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. 26829
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate relationships or comparisons between different entities

    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
     is
    -0.80
     a
    -0.65
     an
    -0.60
     sheet
    -0.59
     was
    -0.58
     en
    -0.57
    ase
    -0.56
     sur
    -0.56
    minus
    -0.56
    一种
    -0.55
    POSITIVE LOGITS
    ſelves
    0.85
     ISNI
    0.84
     '\\;'
    0.81
     leaſt
    0.78
     ainfi
    0.78
     Akismet
    0.77
     tetrach
    0.76
     MainAxisSize
    0.76
     jotka
    0.75
    ValueStyle
    0.75
    Activations Density 0.272%

    No Known Activations