© 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. 0-RES-MATRYOSHKA-DC
    7. 15074
    Prev
    Next
    INDEX
    Explanations

    the act of creating or producing something

    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
    giving
    -0.89
    Helping
    -0.88
    helping
    -0.86
     helping
    -0.86
    unnitel
    -0.82
     AssemblyVersion
    -0.80
     Giving
    -0.78
    Giving
    -0.77
     giving
    -0.74
     Allowing
    -0.74
    POSITIVE LOGITS
     making
    0.53
    χο
    0.47
    聯合
    0.47
    やって
    0.46
    IUrlHelper
    0.46
     tekem
    0.45
    k
    0.45
     église
    0.45
     algas
    0.45
    P
    0.45
    Activations Density 0.012%

    No Known Activations