© 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. 203
    Prev
    Next
    INDEX
    Explanations

    equations and functions using the variable 'w'

    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
     InputDecoration
    -0.86
    SequentialGroup
    -0.81
     ProtoMessage
    -0.81
    日閲覧
    -0.78
     صوتيه
    -0.77
    protoimpl
    -0.76
     المعيارى
    -0.75
     للاسماء
    -0.75
    onAttach
    -0.75
    فرة
    -0.75
    POSITIVE LOGITS
     W
    1.17
    w
    1.10
    W
    1.07
     w
    1.02
    wo
    0.99
    ew
    0.96
     Waw
    0.93
    WSTR
    0.88
     Wnt
    0.88
     Wi
    0.88
    Activations Density 3.165%

    No Known Activations