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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14038
    Prev
    Next
    INDEX
    Explanations

    complex mathematical expressions and high-precision numerical constants

    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
    big
    -0.77
     big
    -0.65
     git
    -0.62
    biggest
    -0.62
     biggest
    -0.61
    bigger
    -0.59
     Worse
    -0.56
     intermédiaire
    -0.56
     bigger
    -0.55
     grosso
    -0.54
    POSITIVE LOGITS
    Big
    0.90
    ViewFeatures
    0.81
     Big
    0.79
    +#+#
    0.69
    writeFieldEnd
    0.64
    SerializedSize
    0.63
     BrowserModule
    0.63
     '\\;'
    0.62
    writeField
    0.59
    maktadır
    0.58
    Activations Density 0.010%

    No Known Activations