© 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. 1-RES-MATRYOSHKA-DC
    7. 979
    Prev
    Next
    INDEX
    Explanations

    mentions of molecules or structures containing viral DNA or nucleic acids

    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
    ModelBuilder
    -0.56
    ществ
    -0.55
    phology
    -0.49
    ///</
    -0.49
    szy
    -0.48
     entanto
    -0.47
    veda
    -0.47
    HKEY
    -0.47
    tispiece
    -0.47
    ngOnInit
    -0.46
    POSITIVE LOGITS
     contain
    3.94
     containing
    3.81
     Containing
    3.69
     Contain
    3.67
     contains
    3.58
    contain
    3.45
     Contains
    3.41
     CONTAIN
    3.41
    containing
    3.33
     contained
    3.27
    Activations Density 0.512%

    No Known Activations