© 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. 1628
    Prev
    Next
    INDEX
    Explanations

    phrases about personal family relationships, especially parents and children

    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
     Люди
    -0.63
    SBATCH
    -0.59
    áneo
    -0.58
    UserRepository
    -0.57
    ariato
    -0.55
    UserDao
    -0.54
    WaitGroup
    -0.53
    delwed
    -0.53
     ľudí
    -0.52
    illoma
    -0.51
    POSITIVE LOGITS
     children
    1.90
     child
    1.60
     kids
    1.56
    children
    1.43
     young
    1.30
     kid
    1.27
     enfants
    1.27
     CHILDREN
    1.24
    kids
    1.23
     youngsters
    1.20
    Activations Density 0.967%

    No Known Activations