© 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. 6-RES-MATRYOSHKA-DC
    7. 512
    Prev
    Next
    INDEX
    Explanations

    the words "mode," "indent," numbers and words with capitalization in the middle, possibly related to code or clinical data

    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
     Bors
    -0.92
    (“
    -0.85
    ”
    -0.78
    :”
    -0.78
     (“
    -0.77
    “
    -0.76
    :“
    -0.73
     Brodie
    -0.73
    áld
    -0.72
     scha
    -0.71
    POSITIVE LOGITS
    ValueStyle
    1.04
     Hobbes
    0.88
    modes
    0.85
     Gegenteil
    0.85
    ¿½
    0.84
    Hayes
    0.83
    CreateMap
    0.81
     gracilis
    0.80
     Modes
    0.79
    Spencer
    0.79
    Activations Density 3.618%

    No Known Activations