© 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. 0-RES-MATRYOSHKA-DC
    7. 14388
    Prev
    Next
    INDEX
    Explanations

    references to statistical tests and analyses

    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
    AccessorTable
    -0.69
    AttributeSet
    -0.62
     fieldNum
    -0.62
    ValueGenerated
    -0.59
     ModelExpression
    -0.58
    JNIEnv
    -0.58
    DockStyle
    -0.57
    usermodel
    -0.56
    Filmo
    -0.56
     DbContext
    -0.55
    POSITIVE LOGITS
    uls
    3.77
    ULS
    2.39
    ulse
    1.16
    ulsar
    0.82
    puls
    0.82
    ulso
    0.81
     Puls
    0.79
     kasarigan
    0.70
     puls
    0.65
    ulsion
    0.63
    Activations Density 0.000%

    No Known Activations