© 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. 3-RES-MATRYOSHKA-DC
    7. 2092
    Prev
    Next
    INDEX
    Explanations

    character sequences in URLs and SSH keys

    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
    CodedInputStream
    -0.73
     Obrador
    -0.72
     Numerade
    -0.70
    DockStyle
    -0.69
    ToScroll
    -0.69
    AccessorTable
    -0.66
     Malabar
    -0.65
    mappedBy
    -0.64
    PyExc
    -0.64
     BitmapFactory
    -0.63
    POSITIVE LOGITS
    Zunanje
    0.53
    Y
    0.50
    ueves
    0.50
     Y
    0.49
    eken
    0.48
    mbolo
    0.47
    M
    0.46
     all
    0.46
    Presentación
    0.46
    把我
    0.46
    Activations Density 0.052%

    No Known Activations