© 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. 10920
    Prev
    Next
    INDEX
    Explanations

    instances of the abbreviation "COM", likely referring to communication ports or related technical terms

    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
    ImageContext
    -1.09
    AddTagHelper
    -1.09
    دانشنامهٔ
    -1.05
     cherchés
    -1.04
    styleType
    -1.04
    ########.
    -1.02
    InjectAttribute
    -0.98
     nahilalakip
    -0.98
     оригіналу
    -0.95
     NSCoder
    -0.94
    POSITIVE LOGITS
     COM
    1.09
    COM
    1.08
     com
    1.02
    com
    0.98
    Com
    0.89
     Com
    0.86
     kom
    0.81
    al
    0.71
    mpo
    0.70
    om
    0.69
    Activations Density 0.013%

    No Known Activations