© 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. 1402
    Prev
    Next
    INDEX
    Explanations

    the word "rap", and sometimes words that simply *contain* "rap", often in medical or technical contexts, and sometimes with a hint of peptides.

    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
     propOrder
    -0.68
    o
    -0.64
     BrowserModule
    -0.63
    oke
    -0.62
    oci
    -0.58
    ov
    -0.58
    obj
    -0.58
    ose
    -0.57
     AssemblyCulture
    -0.57
    providedIn
    -0.57
    POSITIVE LOGITS
    pable
    0.49
    ed
    0.48
    eak
    0.47
    hoto
    0.45
    ⿴
    0.45
    니다
    0.44
     Jop
    0.44
    oly
    0.42
    otent
    0.42
    hotos
    0.41
    Activations Density 0.772%

    No Known Activations