© 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. 805
    Prev
    Next
    INDEX
    Explanations

    error messages related to programming and data type conversions

    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
    gestone
    -0.58
    日閲覧
    -0.57
     CommonModule
    -0.57
    FunctionFlags
    -0.57
     VIDEOTAPE
    -0.56
    MemoryWarning
    -0.55
     hemma
    -0.53
    patra
    -0.53
     gré
    -0.52
    Portály
    -0.52
    POSITIVE LOGITS
     otomatig
    0.60
    bootstrapcdn
    0.59
     treo
    0.52
     Too
    0.50
    っぱり
    0.49
     Couldn
    0.48
    IsContent
    0.47
    Too
    0.46
    PendingIntent
    0.46
     تعريف
    0.45
    Activations Density 0.813%

    No Known Activations