© 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. 3-RES-MATRYOSHKA-DC
    7. 1078
    Prev
    Next
    INDEX
    Explanations

    phrases of the form "refers to" and "consists of"

    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
    ullable
    -0.57
     placed
    -0.48
    massen
    -0.47
    massa
    -0.46
    cepan
    -0.42
    thmus
    -0.42
    arParams
    -0.41
     mids
    -0.41
    DockStyle
    -0.40
     Wohnzimmer
    -0.40
    POSITIVE LOGITS
    BeginInit
    0.69
     مشين
    0.62
    icago
    0.60
     Wikimedijinoj
    0.59
    SuppressMessage
    0.59
     personalizadas
    0.58
    Jereo
    0.58
    AnimationsModule
    0.56
    !("{}",
    0.56
     invokingState
    0.55
    Activations Density 4.925%

    No Known Activations