© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 32009
    Prev
    Next
    INDEX
    Explanations

    terms related to biochemical or cellular processes, particularly those involving receptors, energy regulation, and cell transitions

    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
    Negative Logits
    TemporalType
    -0.69
    Ծանոթ
    -0.49
    oneofs
    -0.48
     jLabel
    -0.47
    ècie
    -0.47
    HasOne
    -0.46
     jo
    -0.46
     فريبيس
    -0.45
    HasForeignKey
    -0.45
     kins
    -0.45
    POSITIVE LOGITS
     Alternatively
    0.58
    FormTagHelper
    0.54
    MessageTagHelper
    0.54
     surla
    0.54
    MLLoader
    0.52
    ForValue
    0.52
     ExecuteAsync
    0.51
    ituary
    0.51
    허
    0.51
    insic
    0.49
    Activations Density 0.447%

    No Known Activations