© 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. 2-RES-MATRYOSHKA-DC
    7. 4417
    Prev
    Next
    INDEX
    Explanations

    the topological value of a magnetic field-related parameter

    oai_token-act-pair · gpt-4.1-nano
    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
     propOrder
    -0.88
    Values
    -0.84
     Values
    -0.81
     VALUES
    -0.80
     ujednoznacz
    -0.80
    values
    -0.78
    VALUES
    -0.75
    曖昧さ回避
    -0.73
     values
    -0.71
    MigrationBuilder
    -0.71
    POSITIVE LOGITS
     stør
    0.56
     location
    0.55
    Pers
    0.49
    setTimeout
    0.47
    nitt
    0.46
     lati
    0.46
     ſmall
    0.46
    SOUNDBITE
    0.46
    роят
    0.45
    UnusedPrivate
    0.45
    Activations Density 0.049%

    No Known Activations