© 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. 299
    Prev
    Next
    INDEX
    Explanations

    LaTeX code for displaying mathematical expressions

    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
     ویکی‌پدیای
    -1.01
    ReusableCell
    -0.98
    __':
    -0.97
     AttributeSet
    -0.94
    Datuak
    -0.94
    
    -0.94
     propOrder
    -0.92
     يتيمه
    -0.91
    ModelSerializer
    -0.91
    OGND
    -0.91
    POSITIVE LOGITS
    left
    1.66
     left
    1.38
    Left
    1.31
     Left
    1.25
    LEFT
    1.17
    getLeft
    1.14
     LEFT
    1.09
    lef
    1.02
    setLeft
    0.95
    right
    0.94
    Activations Density 0.902%

    No Known Activations