© 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. 3523
    Prev
    Next
    INDEX
    Explanations

    references to duplicate content or duplication

    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
    parsedMessage
    -0.75
    Hentet
    -0.70
    AfterViewInit
    -0.68
    Referencies
    -0.60
    Filmographie
    -0.60
     مرئيه
    -0.59
     beginnetje
    -0.59
    ')['
    -0.59
    Heck
    -0.59
    contrib
    -0.58
    POSITIVE LOGITS
     duplicate
    2.81
     Duplicate
    2.63
     duplicates
    2.53
    Duplicate
    2.34
    duplicate
    2.25
     duplicated
    2.23
     duplication
    2.19
     dup
    1.90
    duplicates
    1.88
     Dup
    1.77
    Activations Density 0.031%

    No Known Activations