© 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. 1970
    Prev
    Next
    INDEX
    Explanations

    mentions in physics, math, geography, and religion.

    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
    Dwayne
    -1.01
    aktery
    -0.91
     Dwayne
    -0.91
    JspWriter
    -0.87
     Schur
    -0.84
     Gaylord
    -0.84
     Datenschutzer
    -0.83
    الإنجليزية
    -0.82
     coû
    -0.81
     Indoch
    -0.80
    POSITIVE LOGITS
     radio
    0.80
     Rad
    0.76
    eso
    0.75
     Farn
    0.75
    nu
    0.74
     Radio
    0.72
    BCF
    0.72
    Radio
    0.71
    CommonModule
    0.71
    RADIO
    0.71
    Activations Density 4.709%

    No Known Activations