© 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. 2-RES-MATRYOSHKA-DC
    7. 4833
    Prev
    Next
    INDEX
    Explanations

    references to upward movement or increases

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InjectAttribute
    -0.68
    ScopeManager
    -0.65
    Hör
    -0.63
     jelasnya
    -0.61
     Halen
    -0.61
    Erreferentziak
    -0.60
     تضيفلها
    -0.58
     externi
    -0.58
     Exc
    -0.58
    internalType
    -0.58
    POSITIVE LOGITS
    interopRequire
    0.60
    Diweddarwch
    0.56
     bleek
    0.55
     blijkt
    0.54
    DESCRIPTOR
    0.53
    ization
    0.52
    IGATION
    0.52
    andExpect
    0.52
    ویت
    0.52
    mphony
    0.52
    Activations Density 0.034%

    No Known Activations