© 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. 6663
    Prev
    Next
    INDEX
    Explanations

    lines of punctuation, mostly commas and periods

    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
    SharedCtor
    -0.81
    kirakan
    -0.50
     communis
    -0.50
    ")->
    -0.49
    yordu
    -0.49
    "]);
    -0.48
     varsa
    -0.46
    Buildable
    -0.46
    gios
    -0.46
     electrolytic
    -0.46
    POSITIVE LOGITS
    abestanden
    0.73
    StandardCharsets
    0.68
    NUMX
    0.64
    Portály
    0.60
    üten
    0.58
    Referencie
    0.58
    Œuvres
    0.57
    cipy
    0.54
     ActionListener
    0.54
     dark
    0.54
    Activations Density 0.571%

    No Known Activations