© 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. 24-RES-MATRYOSHKA-DC
    7. 1598
    Prev
    Next
    INDEX
    Explanations

    the words "wild" or "input" or the string "ref"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     nahilalakip
    -0.67
     насељу
    -0.64
    MLLoader
    -0.57
    AccessorTable
    -0.54
    CppMethod
    -0.51
     AssemblyCulture
    -0.50
    RegistryLite
    -0.50
    icznie
    -0.48
    urably
    -0.48
     OFDb
    -0.47
    POSITIVE LOGITS
     type
    3.47
    type
    3.09
     Type
    2.66
     TYPE
    2.59
    Type
    2.56
     types
    2.44
    TYPE
    2.36
     tipo
    2.30
    类型
    2.05
    getType
    2.03
    Activations Density 0.700%

    No Known Activations