© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 177
    Prev
    Next
    INDEX
    Explanations

    instances of ordinal numbers or sequences in text

    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
    hésite
    -0.80
    
    -0.79
    ;'>
    -0.75
     mourut
    -0.75
     Krieger
    -0.74
     myſelf
    -0.74
    anneer
    -0.73
    pincode
    -0.73
    woordig
    -0.72
     Efq
    -0.72
    POSITIVE LOGITS
    FIRST
    1.42
     First
    1.41
     first
    1.40
     FIRST
    1.36
    First
    1.30
    first
    1.23
     third
    1.12
     second
    1.05
    第一
    1.04
    isFirst
    1.04
    Activations Density 0.998%

    No Known Activations