© 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. 32643
    Prev
    Next
    INDEX
    Explanations

    references to tidal conditions

    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
     Kab
    -0.79
     kab
    -0.73
     Abbe
    -0.67
     doInBackground
    -0.66
    terase
    -0.66
    kab
    -0.65
     Albin
    -0.65
    Kab
    -0.64
     tric
    -0.64
     espar
    -0.64
    POSITIVE LOGITS
     Tide
    1.71
     tide
    1.62
    Tidal
    1.59
     tidal
    1.59
    Tide
    1.54
     tides
    1.48
     Tidal
    1.45
    tidal
    1.41
     Tides
    1.38
    tide
    1.05
    Activations Density 0.002%

    No Known Activations