© 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. 3339
    Prev
    Next
    INDEX
    Explanations

    instances of the word "pure," particularly "pure" used as an adjective or descriptor within the text

    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
     Ike
    -0.66
    complexContent
    -0.58
    Ike
    -0.57
     Marvin
    -0.55
    rangle
    -0.54
    printStackTrace
    -0.53
     hangat
    -0.51
    Civic
    -0.51
    itude
    -0.50
    oog
    -0.50
    POSITIVE LOGITS
     pure
    3.66
    pure
    3.52
     Pure
    3.48
    Pure
    3.48
     PURE
    3.09
    PURE
    2.88
     purest
    2.42
     purer
    2.19
    纯
    2.11
     puro
    2.08
    Activations Density 0.007%

    No Known Activations