© 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. 6-RES-MATRYOSHKA-DC
    7. 50
    Prev
    Next
    INDEX
    Explanations

    conjunctions and discourse markers used to connect ideas

    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
     myſelf
    -1.09
     Chriftian
    -1.02
     Monfieur
    -1.02
     Majefty
    -1.00
     Jefus
    -0.98
     greateſt
    -0.96
     themſelves
    -0.95
     Efq
    -0.94
     pleaſure
    -0.92
    ſelf
    -0.90
    POSITIVE LOGITS
     szóci
    0.85
     שוליים
    0.84
    <bos>
    0.75
     perhaps
    0.75
    たまた
    0.71
    </i>
    0.68
     certainly
    0.68
     it
    0.66
    rungsseite
    0.66
    Hozzáférés
    0.66
    Activations Density 7.739%

    No Known Activations