© 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. 4859
    Prev
    Next
    INDEX
    Explanations

    specific actions related to user role assignments or modifications

    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
    WithIdentifier
    -0.75
     getIntent
    -0.73
     getArguments
    -0.70
     JFrame
    -0.66
    getDoctrine
    -0.66
    Xna
    -0.65
    AsUp
    -0.65
     CURLOPT
    -0.65
     UIColor
    -0.64
     XNUMX
    -0.63
    POSITIVE LOGITS
    enosis
    0.68
    帖最后由
    0.68
     propOrder
    0.65
    AnchorStyles
    0.63
    itonitis
    0.62
     Vikipedi
    0.59
    tedly
    0.59
     Chwiliwch
    0.59
    FileVersion
    0.58
     MenuView
    0.57
    Activations Density 0.140%

    No Known Activations