© 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. 25511
    Prev
    Next
    INDEX
    Explanations

    phrases indicating statistical estimates or predictions about quantities or occurrences

    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
     Minato
    -0.56
     prediction
    -0.56
     Prediction
    -0.55
     mío
    -0.55
    uttosto
    -0.54
     predicts
    -0.53
     cures
    -0.53
     Whig
    -0.53
     wigs
    -0.52
     Teflon
    -0.52
    POSITIVE LOGITS
     AssemblyProduct
    0.79
    enumii
    0.77
    routeProvider
    0.74
    Personendaten
    0.72
     المعيارى
    0.69
    Portály
    0.67
    stateProvider
    0.66
    oston
    0.64
    EndInit
    0.64
     Espinosa
    0.64
    Activations Density 0.009%

    No Known Activations