© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13864
    Prev
    Next
    INDEX
    Explanations

    references to types or categories of things, particularly focusing on descriptions of a 'kind' or 'type' of object, device, or discussion

    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
    يميديا
    -0.62
     <<<<<<<<<<<<<<
    -0.60
    뀐
    -0.57
    providedIn
    -0.54
    例句
    -0.52
    athed
    -0.50
     виправивши
    -0.50
    뀌
    -0.50
     ligiloj
    -0.48
     Ở
    -0.48
    POSITIVE LOGITS
     anytime
    0.79
    RenderAtEndOf
    0.77
    AndEndTag
    0.71
    anything
    0.70
    ftagPool
    0.70
     anywhere
    0.68
    Anytime
    0.67
     Efq
    0.65
     anything
    0.65
     Anywhere
    0.65
    Activations Density 0.166%

    No Known Activations