© 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. 749
    Prev
    Next
    INDEX
    Explanations

    terms related to data processing and memory management in technology or programming contexts

    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
    forRoot
    -0.57
    richTextPanel
    -0.55
    acheco
    -0.53
    atzung
    -0.52
     Bioinformatics
    -0.51
     թվական
    -0.50
     atrop
    -0.50
     tocado
    -0.50
     aeruginosa
    -0.50
     krwi
    -0.49
    POSITIVE LOGITS
     protoimpl
    0.77
     '\\;'
    0.74
    StoryboardSegue
    0.72
    AutoScaleMode
    0.60
     Meksiku
    0.59
    archiviato
    0.59
    nocache
    0.59
    )}_
    0.56
    aboo
    0.55
    ("%.
    0.55
    Activations Density 0.739%

    No Known Activations