© 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. 2714
    Prev
    Next
    INDEX
    Explanations

    references to spam moderation and related instructions

    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
     estimés
    -0.74
    typeorm
    -0.63
    __':
    -0.61
    Tikang
    -0.60
    setAccessible
    -0.59
    __":
    -0.57
    hawatir
    -0.56
    ceptre
    -0.56
     handshake
    -0.55
    ayaquil
    -0.54
    POSITIVE LOGITS
     <>",
    0.54
    ļas
    0.54
     ped
    0.47
     الحره
    0.47
    存于互联网档案馆
    0.46
    EDEFAULT
    0.46
    이버
    0.46
    XmlAccessType
    0.45
    bsd
    0.44
     SPL
    0.44
    Activations Density 2.270%

    No Known Activations