© 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. 1-RES-MATRYOSHKA-DC
    7. 897
    Prev
    Next
    INDEX
    Explanations

    segments related to preprocessing or preparatory steps

    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
     previous
    -0.74
     предыду
    -0.64
    previous
    -0.63
     Previous
    -0.58
     earlier
    -0.56
    Previous
    -0.55
    earlier
    -0.55
     прошло
    -0.54
     capito
    -0.54
     прошлом
    -0.54
    POSITIVE LOGITS
     pre
    4.59
     Pre
    4.16
    Pre
    4.16
    pre
    4.13
     PRE
    3.39
    PRE
    3.34
     pré
    3.03
    预
    2.47
     Pré
    2.25
    pré
    2.20
    Activations Density 0.284%

    No Known Activations