© 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. 2-RES-MATRYOSHKA-DC
    7. 5678
    Prev
    Next
    INDEX
    Explanations

    references to the structural components called telomeres, specifically the term "telomere" and its variations

    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
    Dragged
    -0.65
    __(/*!
    -0.61
     noDo
    -0.60
    attaa
    -0.58
    IVEREF
    -0.57
     SEEK
    -0.57
    ]<<"
    -0.57
     sobra
    -0.56
    roscope
    -0.56
    GEBURTSDATUM
    -0.56
    POSITIVE LOGITS
    omer
    3.78
    omers
    2.83
    omere
    2.59
    omeric
    2.44
     isomer
    1.14
    imer
    0.79
     isomers
    0.77
    NamedQueries
    0.69
    umer
    0.69
    mer
    0.66
    Activations Density 0.003%

    No Known Activations