© 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. 1619
    Prev
    Next
    INDEX
    Explanations

    the words "serial" and "Tony", as well as programming and networking terms

    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
    TagMode
    -0.92
     Murat
    -0.85
     Foxx
    -0.85
     Fox
    -0.82
     Muhammed
    -0.82
     fox
    -0.81
     foxes
    -0.80
     Shapiro
    -0.79
    fox
    -0.79
    esgue
    -0.78
    POSITIVE LOGITS
     Geraldine
    0.80
    providedIn
    0.77
     Falk
    0.71
    "><?=
    0.70
    ">{{$
    0.69
     infer
    0.68
     Tada
    0.67
     Warrant
    0.65
    proto
    0.65
    berus
    0.65
    Activations Density 4.583%

    No Known Activations