© 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. 2-RES-MATRYOSHKA-DC
    7. 5914
    Prev
    Next
    INDEX
    Explanations

    references to authors with specific and prominent last initials

    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
    Datuak
    -1.13
     незавершена
    -1.08
    Personensuche
    -1.02
    bewerken
    -1.02
    IntoConstraints
    -1.00
    ReusableCell
    -0.99
     kasarigan
    -0.99
     tartalomajánló
    -0.93
     estekak
    -0.91
    CodeAttribute
    -0.89
    POSITIVE LOGITS
     truth
    0.55
    citenamefont
    0.54
     eccl
    0.54
     yü
    0.50
    bibinfo
    0.47
    Processed
    0.47
     charged
    0.46
     fasc
    0.46
    Phyllis
    0.45
    줍
    0.45
    Activations Density 0.489%

    No Known Activations