© 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. 3-RES-MATRYOSHKA-DC
    7. 2581
    Prev
    Next
    INDEX
    Explanations

    chemical compounds with "glu" or "tide" in their name, and the fragment "tamy"

    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
    XmlAccessorType
    -0.61
    LabelTagHelper
    -0.57
    adpleegd
    -0.52
    sidemargin
    -0.51
    ่วย
    -0.50
    المناصب
    -0.50
    grace
    -0.49
    ;}
    -0.49
     Gas
    -0.48
    脈
    -0.48
    POSITIVE LOGITS
     CreateTagHelper
    0.83
    WriteLiteral
    0.66
     gl
    0.62
    Fprintf
    0.62
    AsUp
    0.55
     gluta
    0.54
    исправ
    0.54
    fährt
    0.54
    исленность
    0.53
    yaar
    0.53
    Activations Density 0.186%

    No Known Activations