© 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. 5167
    Prev
    Next
    INDEX
    Explanations

    references to significant or notable events or occurrences

    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
     occur
    -0.89
     occurred
    -0.85
     occurs
    -0.81
    occur
    -0.78
     occurring
    -0.76
    occurs
    -0.76
     wyst
    -0.75
     occurrence
    -0.74
    Occurs
    -0.72
     Occurrence
    -0.70
    POSITIVE LOGITS
     happen
    1.97
     happens
    1.80
    happen
    1.77
    happens
    1.55
     Happen
    1.45
     happened
    1.44
     HAPP
    1.36
     Happens
    1.32
     happening
    1.29
    happened
    1.17
    Activations Density 0.016%

    No Known Activations