© 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. 10939
    Prev
    Next
    INDEX
    Explanations

    programming syntax and data structure initialization

    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
    le
    -0.50
    ig
    -0.47
    or
    -0.46
    il
    -0.46
    .,
    -0.46
    ii
    -0.45
    cl
    -0.44
    ing
    -0.44
     On
    -0.44
    ch
    -0.43
    POSITIVE LOGITS
     Efq
    1.12
    MemoryWarning
    0.96
    __":
    
    0.94
     myſelf
    0.93
    LEncoder
    0.87
    ArgsConstructor
    0.84
     }}$}
    0.84
     Theſe
    0.83
    endphp
    0.80
     fufficient
    0.79
    Activations Density 0.040%

    No Known Activations