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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 522
    Prev
    Next
    INDEX
    Explanations

    phrases indicating complex processes or requirements involving high levels of effort or expense

    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
    Geplaatst
    -1.06
     Roskov
    -0.91
    клопе
    -0.87
    adə
    -0.87
    GEBURTSDATUM
    -0.86
    脚注の使い方
    -0.81
    AddTagHelper
    -0.79
    EndProject
    -0.77
    Personendaten
    -0.76
     pinulongan
    -0.73
    POSITIVE LOGITS
    才能
    0.62
     expensive
    0.60
     costly
    0.58
     caros
    0.56
     tedious
    0.55
     laborious
    0.49
     coûte
    0.46
     Expensive
    0.45
    費
    0.45
     cont
    0.44
    Activations Density 1.426%

    No Known Activations