© 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. 4243
    Prev
    Next
    INDEX
    Explanations

    references to dust, smoke, or particulates

    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
     cref
    -0.68
     APL
    -0.68
    Autoritní
    -0.63
    diad
    -0.62
    ELTS
    -0.60
    Пото
    -0.60
    Calla
    -0.60
     Whal
    -0.60
    WebControls
    -0.58
    viders
    -0.57
    POSITIVE LOGITS
     dust
    3.47
    dust
    3.02
     Dust
    2.97
    Dust
    2.81
     DUST
    2.52
     poussière
    2.05
     dusting
    1.89
     polvo
    1.83
     dusty
    1.81
     dusted
    1.79
    Activations Density 0.002%

    No Known Activations