© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4731
    Prev
    Next
    INDEX
    Explanations

    references to drainage or drain components in plumbing contexts

    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
    ineno
    -0.73
    onActivityResult
    -0.62
     glassy
    -0.57
    كومة
    -0.56
    ocino
    -0.54
    مصادر
    -0.54
    TEMPO
    -0.54
     BoxDecoration
    -0.54
     Mast
    -0.54
    Mast
    -0.53
    POSITIVE LOGITS
     drain
    3.23
     Drain
    3.02
     drains
    2.83
    Drain
    2.73
    drain
    2.73
     draining
    2.58
     drained
    2.50
     DRAIN
    2.45
    drained
    2.17
     drainage
    2.11
    Activations Density 0.005%

    No Known Activations