© 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. 14801
    Prev
    Next
    INDEX
    Explanations

    phrases related to the removal of substances in biological procedures

    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
    impin
    -0.52
    ganj
    -0.48
     poveznice
    -0.48
    CppMethod
    -0.47
    archiv
    -0.46
     TEMPER
    -0.45
    gate
    -0.44
     Damned
    -0.44
    icep
    -0.43
     informativo
    -0.43
    POSITIVE LOGITS
    TagMode
    0.65
     EconPapers
    0.61
    Personendaten
    0.61
    :✨
    0.61
     BoxDecoration
    0.61
    Spoljašnje
    0.61
     NSCoder
    0.60
    AutoModerator
    0.57
    AndEndTag
    0.57
    ViewImports
    0.56
    Activations Density 0.133%

    No Known Activations