© 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. 2866
    Prev
    Next
    INDEX
    Explanations

    citations that consist of names, dates, and bracketed numbers/symbols

    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
     leaſt
    -0.62
    producción
    -0.59
     Efq
    -0.59
     Anſ
    -0.56
    Gambas
    -0.56
     Inscrivez
    -0.55
     myſelf
    -0.55
     whoſe
    -0.53
     montón
    -0.52
    ocry
    -0.51
    POSITIVE LOGITS
    PMailer
    0.65
    citep
    0.56
    RegressionTest
    0.55
     NSError
    0.54
    saraba
    0.54
    bibitem
    0.50
     AssemblyCompany
    0.50
     Burroughs
    0.47
    rungsseite
    0.47
    ########.
    0.47
    Activations Density 0.903%

    No Known Activations