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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 1210
    Prev
    Next
    INDEX
    Explanations

    lines of code involving print and log functions

    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
     himo
    -0.81
    Revenir
    -0.71
     türlü
    -0.64
    Rujuakan
    -0.60
     seamlessly
    -0.60
     ?>/
    -0.59
     صوتيه
    -0.59
     通販
    -0.58
     hâte
    -0.58
     pitié
    -0.57
    POSITIVE LOGITS
    println
    1.13
    WriteLine
    1.02
    Println
    0.85
     kasarigan
    0.84
     println
    0.84
     print
    0.80
     prints
    0.77
    print
    0.76
    enumi
    0.73
    iostream
    0.73
    Activations Density 0.214%

    No Known Activations