© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5691
    Prev
    Next
    INDEX
    Explanations

    references to the primary or predominant usage of something

    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
     dokonce
    -0.70
     myö
    -0.68
     Majority
    -0.66
     zelfs
    -0.66
    majority
    -0.64
     chi̍t
    -0.61
     dessutom
    -0.60
     câte
    -0.59
     even
    -0.58
     majority
    -0.57
    POSITIVE LOGITS
     mainly
    2.59
     Mainly
    2.42
     mostly
    2.38
     primarily
    2.38
     Mostly
    2.31
    Mostly
    2.31
    mainly
    2.28
    primarily
    2.25
    Mainly
    2.25
    mostly
    2.22
    Activations Density 0.054%

    No Known Activations