© 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. 14349
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "particle."

    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
     electrons
    -1.03
    electrons
    -0.91
     crystals
    -0.86
     fermions
    -0.84
     electron
    -0.84
     atoms
    -0.82
     photons
    -0.81
    electron
    -0.80
    Electron
    -0.78
     Electron
    -0.78
    POSITIVE LOGITS
     particle
    1.89
     Particle
    1.53
    Particle
    1.15
    particle
    1.08
     molecular
    0.61
     party
    0.59
    addPreferredGap
    0.57
    PARTY
    0.56
     Molecular
    0.55
    Odkazy
    0.55
    Activations Density 0.005%

    No Known Activations