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. 18652
    Prev
    Next
    INDEX
    Explanations

    references to specific genetic mutations and their associated exons

    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
    PerformLayout
    -0.76
    UserScript
    -0.72
     Aires
    -0.70
    PPS
    -0.69
    initComponents
    -0.66
     PPS
    -0.65
     Mahoney
    -0.65
     McBride
    -0.65
    idopsis
    -0.64
    utnik
    -0.64
    POSITIVE LOGITS
     exon
    1.15
     splicing
    0.75
     Goliath
    0.66
    ValueStyle
    0.57
     Jekyll
    0.54
    kadang
    0.54
     splice
    0.53
    шк
    0.52
    xca
    0.52
    Reality
    0.52
    Activations Density 0.010%

    No Known Activations