© 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
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13330
    Prev
    Next
    INDEX
    Explanations

    references to high levels of education, particularly emphasizing the concept of being highly educated

    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
     ModelExpression
    -0.98
    tion
    -0.91
     disambiguazione
    -0.76
    bootstrapcdn
    -0.76
    hawatir
    -0.75
    IsMutable
    -0.75
     autorytatywna
    -0.73
    NewUrlParser
    -0.73
    AsUp
    -0.73
    thâu
    -0.71
    POSITIVE LOGITS
    tions
    2.20
    IONS
    0.52
    rique
    0.50
     defStyleAttr
    0.50
    aciones
    0.47
    ps
    0.46
    warmup
    0.46
    atisk
    0.46
     North
    0.45
     tions
    0.45
    Activations Density 0.001%

    No Known Activations