© 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. 3-RES-MATRYOSHKA-DC
    7. 1887
    Prev
    Next
    INDEX
    Explanations

    terms used in technical documentation and coding, especially names assigned to variables or functions as well as descriptions of medical treatments

    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
    ReusableCell
    -0.89
    BeforeEach
    -0.86
    Datuak
    -0.81
    ly
    -0.80
     Kirkpatrick
    -0.78
    writeFieldEnd
    -0.77
     Jessie
    -0.76
     KIR
    -0.73
     Pizarro
    -0.70
    apache
    -0.69
    POSITIVE LOGITS
     Aras
    0.88
     Strips
    0.85
     Anis
    0.82
     Strip
    0.78
    niques
    0.75
     Sturgeon
    0.75
     channels
    0.74
     Stefani
    0.73
     Punk
    0.72
    kohl
    0.71
    Activations Density 4.458%

    No Known Activations