© 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. 32103
    Prev
    Next
    INDEX
    Explanations

    references to specific proteins and signaling pathways, particularly those related to immune response and viral infection

    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
    FetchType
    -0.47
     etc
    -0.45
     maternelle
    -0.44
    nodoc
    -0.43
     next
    -0.42
     Sociales
    -0.42
     promise
    -0.42
    ientôt
    -0.40
    IntoConstraints
    -0.40
    jén
    -0.40
    POSITIVE LOGITS
    InstrumentedTest
    0.84
    IndentedString
    0.76
     насељу
    0.72
    CodedInputStream
    0.66
    tagHelperRunner
    0.65
    LookAnd
    0.62
    ContextHolder
    0.61
     kaarangay
    0.59
    ècie
    0.59
    SuppressMessage
    0.59
    Activations Density 0.032%

    No Known Activations