© 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. 1465
    Prev
    Next
    INDEX
    Explanations

    the word "in" followed by other 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
    Koordinaten
    -0.65
    BibitemShut
    -0.65
     Getter
    -0.65
    CodeAttribute
    -0.63
    shadowOpacity
    -0.63
    twimg
    -0.60
    étranger
    -0.58
    താ
    -0.56
     StringUtil
    -0.55
    havior
    -0.55
    POSITIVE LOGITS
     IN
    0.83
     In
    0.83
    In
    0.77
    IN
    0.61
     Into
    0.58
    getIn
    0.58
     INTO
    0.57
     unin
    0.57
     InputDecoration
    0.56
    IsIn
    0.55
    Activations Density 0.493%

    No Known Activations