© 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. 3-RES-MATRYOSHKA-DC
    7. 802
    Prev
    Next
    INDEX
    Explanations

    mathematical equations in LaTeX format

    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
     Morel
    -0.65
    ${
    -0.65
     ${
    -0.59
    ing
    -0.58
    +"'
    -0.58
    ******/
    -0.57
    (${
    -0.56
     wsz
    -0.56
    optarg
    -0.56
    visibility
    -0.55
    POSITIVE LOGITS
    {\
    2.20
     {\
    1.16
    ){\
    0.89
    ]{\
    0.87
    évaluateur
    0.86
    mybatisplus
    0.85
     Guth
    0.75
    {(\
    0.74
    *{\
    0.73
    Composable
    0.72
    Activations Density 0.187%

    No Known Activations