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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16698
    Prev
    Next
    INDEX
    Explanations

    percentages related to prevalence statistics

    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
    SourceChecksum
    -0.98
    AddTagHelper
    -0.93
     AssemblyVersion
    -0.91
    webElementXpaths
    -0.91
     indisponible
    -0.90
    %?
    -0.89
     $\%
    -0.88
     PERCENT
    -0.87
     %)
    -0.85
     وتسجيلات
    -0.85
    POSITIVE LOGITS
     fratelli
    0.45
     számára
    0.45
     in
    0.41
     shutil
    0.41
    endereco
    0.40
     часы
    0.39
    cope
    0.39
     juist
    0.39
    
    0.38
    closePath
    0.38
    Activations Density 0.027%

    No Known Activations