Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 25202
    Prev
    Next
    INDEX
    Explanations

    terms related to the structure and types of DNA strands

    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
     Mep
    -0.85
     InputDecoration
    -0.83
     rito
    -0.80
     pinulongan
    -0.78
    awtextra
    -0.77
    enumi
    -0.75
     OpenAPI
    -0.74
     civ
    -0.73
     vuitton
    -0.72
     Wentworth
    -0.72
    POSITIVE LOGITS
     strand
    1.34
    Strand
    1.26
     Strand
    1.19
    stranded
    1.13
     strands
    1.12
    strand
    1.10
     stranded
    0.84
    trand
    0.69
    ●●
    0.66
    Bree
    0.58
    Activations Density 0.004%

    No Known Activations