© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 7322
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "nothing" or the idea of emptiness or absence

    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
    someone
    -0.97
     someone
    -0.92
    somebody
    -0.92
    Someone
    -0.91
     somebody
    -0.90
    Somebody
    -0.88
     SOMEONE
    -0.84
     Someone
    -0.82
     ControllerBase
    -0.81
     somewhere
    -0.80
    POSITIVE LOGITS
     nothing
    3.03
    nothing
    2.80
    Nothing
    2.69
     Nothing
    2.66
     NOTHING
    2.17
    NOTHING
    2.03
     rien
    1.76
     nothin
    1.71
     nada
    1.63
     nichts
    1.55
    Activations Density 0.010%

    No Known Activations