© 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. 4388
    Prev
    Next
    INDEX
    Explanations

    references to the chemical element nickel

    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
    AutoScale
    -0.72
    endphp
    -0.70
    SequentialGroup
    -0.67
     Schaff
    -0.64
    Попис
    -0.64
     Hib
    -0.62
     AssemblyTitle
    -0.60
     Alam
    -0.59
    ługość
    -0.58
     hasard
    -0.58
    POSITIVE LOGITS
     Che
    3.38
    Che
    3.30
    che
    3.11
     che
    3.09
     CHE
    2.84
    CHE
    2.70
     chemo
    1.72
     Chel
    1.71
    chel
    1.69
     cheats
    1.63
    Activations Density 0.129%

    No Known Activations