© 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. 25351
    Prev
    Next
    INDEX
    Explanations

    terms related to events and sequences concerning existence and transitions

    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
     myſelf
    -0.69
     مشين
    -0.68
     Waray
    -0.68
     uſed
    -0.66
     greateſt
    -0.64
    ſelves
    -0.61
     raiſ
    -0.61
     Jefus
    -0.60
    bbene
    -0.60
     pleaſure
    -0.60
    POSITIVE LOGITS
     until
    1.00
     till
    0.90
    until
    0.89
     Until
    0.85
     UNTIL
    0.83
     hasta
    0.82
    Until
    0.80
     til
    0.75
     Till
    0.75
     até
    0.74
    Activations Density 0.036%

    No Known Activations