© 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. 1412
    Prev
    Next
    INDEX
    Explanations

    terms associated with DNA, programming code, and web-related markup languages

    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
    oredCriteria
    -0.66
    raszamy
    -0.64
     montón
    -0.63
    modelBuilder
    -0.62
    Tikang
    -0.61
    CppMethod
    -0.60
     Efq
    -0.60
     lenker
    -0.59
     насељу
    -0.58
    lious
    -0.56
    POSITIVE LOGITS
    󠁢
    0.68
    idopsis
    0.66
     للمعارف
    0.63
    LowerCase
    0.61
    SequentialGroup
    0.60
    fxml
    0.59
    Itoa
    0.58
    śred
    0.56
    createServer
    0.56
    ethane
    0.56
    Activations Density 1.073%

    No Known Activations