© 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. 1051
    Prev
    Next
    INDEX
    Explanations

    the string "bar" and strings closely associated with it, such as "baz" or "code"

    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
     متعلقه
    -1.13
    ")}
    -0.59
    udt
    -0.57
    urns
    -0.57
    nantes
    -0.57
     RVA
    -0.57
    Dakota
    -0.56
     Ache
    -0.56
    ,))
    -0.56
     Dakota
    -0.54
    POSITIVE LOGITS
     bar
    3.44
    bar
    3.20
     Bar
    3.08
    Bar
    3.02
     bars
    2.91
    BAR
    2.81
     BAR
    2.70
    bars
    2.69
     Bars
    2.61
    Bars
    2.47
    Activations Density 0.327%

    No Known Activations