© 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. 0-RES-MATRYOSHKA-DC
    7. 11405
    Prev
    Next
    INDEX
    Explanations

    references to the concept of digital or electronic redemption

    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
    ########.
    -0.82
     chi̍t
    -0.62
     resourceCulture
    -0.62
    íncia
    -0.60
    Tikang
    -0.60
     Dider
    -0.60
     setuptools
    -0.58
     Maje
    -0.57
     /\.
    -0.57
     Vey
    -0.56
    POSITIVE LOGITS
     redemption
    3.36
     rede
    3.27
     redeem
    3.25
     redeemed
    2.94
    Rede
    2.73
     Redemption
    2.72
    rede
    2.69
     Rede
    2.61
     redeeming
    2.56
     Redeemer
    1.49
    Activations Density 0.001%

    No Known Activations