© 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. 17234
    Prev
    Next
    INDEX
    Explanations

    phrases related to initial conditions and configurations in simulations

    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
     initial
    -0.58
     internazionali
    -0.56
     пот
    -0.55
    reggio
    -0.55
     internacionais
    -0.54
     Truss
    -0.54
    ַת
    -0.53
     suor
    -0.53
     Erster
    -0.51
    ூர்
    -0.50
    POSITIVE LOGITS
    StoryboardSegue
    0.81
    tvguidetime
    0.80
     ModelExpression
    0.79
    بوابة
    0.72
    contentLoaded
    0.71
     /\.(
    0.70
    LookAnd
    0.70
     незавершена
    0.69
     /\.
    0.69
    Portale
    0.68
    Activations Density 0.005%

    No Known Activations