© 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. 6-RES-MATRYOSHKA-DC
    7. 689
    Prev
    Next
    INDEX
    Explanations

    modified forms of words, especially past participles, often ending in -ed, -ized, or related to transformation

    oai_token-act-pair · gemini-2.0-flash
    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
    forth
    -0.66
    しまいます
    -0.62
    Enllaços
    -0.62
    ropolitan
    -0.59
    wide
    -0.58
     Chwiliwch
    -0.56
    Nuorodos
    -0.55
    stron
    -0.54
    urcht
    -0.53
    frain
    -0.53
    POSITIVE LOGITS
    ruptedException
    0.79
    readObject
    0.77
    MeasureSpec
    0.73
    ogaster
    0.73
    cled
    0.69
    ibatis
    0.68
     Initialized
    0.65
    XmlAccessorType
    0.65
    ✨:
    0.64
     propOrder
    0.64
    Activations Density 1.267%

    No Known Activations