© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 14114
    Prev
    Next
    INDEX
    Explanations

    references to specific models and formats related to business strategies or processes

    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
     improvements
    -0.68
     suitability
    -0.65
     enhancements
    -0.65
     modifications
    -0.63
     improved
    -0.55
     upgrades
    -0.55
     aspects
    -0.54
     Осо
    -0.54
    zug
    -0.53
    improved
    -0.53
    POSITIVE LOGITS
    новниш
    0.89
    SequentialGroup
    0.76
     jadx
    0.73
    windowFixed
    0.71
    enderror
    0.69
    GEBURTSDATUM
    0.68
    RunWith
    0.67
     ostavi
    0.66
     MaterialApp
    0.65
     Vorge
    0.64
    Activations Density 0.191%

    No Known Activations