Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 14104
    Prev
    Next
    INDEX
    Explanations

    terms related to Lévy processes and related mathematical concepts

    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
     myſelf
    -0.89
     Monfieur
    -0.85
     Theſe
    -0.82
     himſelf
    -0.81
     occaf
    -0.80
     itſelf
    -0.80
     themſelves
    -0.79
     ་་
    -0.78
     Jefus
    -0.78
     diſt
    -0.77
    POSITIVE LOGITS
    sizeCache
    0.65
    Datuak
    0.65
     nahilalakip
    0.61
    országban
    0.60
    AutoField
    0.58
    ThroughAttribute
    0.58
    complexContent
    0.57
    oredCriteria
    0.56
     Den
    0.56
    PreExecute
    0.55
    Activations Density 0.027%

    No Known Activations