© 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. 18-RES-MATRYOSHKA-DC
    7. 1487
    Prev
    Next
    INDEX
    Explanations

    sentences that use transition words

    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.18.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.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    SequentialGroup
    -0.70
    AndEndTag
    -0.65
    Personensuche
    -0.61
     Exacts
    -0.60
    AddHtmlAttribute
    -0.58
    olm
    -0.57
     obwohl
    -0.56
    EndGlobal
    -0.56
    '>{
    -0.55
    BufferException
    -0.55
    POSITIVE LOGITS
     conversely
    1.48
     Conversely
    1.40
     meanwhile
    1.37
     natomiast
    1.30
    Conversely
    1.27
     Meanwhile
    1.25
     hingegen
    1.23
    Meanwhile
    1.19
     Similarly
    1.18
     Likewise
    1.17
    Activations Density 1.421%

    No Known Activations