© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13675
    Prev
    Next
    INDEX
    Explanations

    recognition of specific technical terms and concepts related to advanced scientific topics

    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
    Eloquent
    -0.60
    enumi
    -0.58
     rospy
    -0.56
     محفوظة
    -0.55
    BASEPATH
    -0.55
     Económica
    -0.55
    ibatis
    -0.54
    URLException
    -0.54
    \}\\
    -0.54
    jsxFileName
    -0.53
    POSITIVE LOGITS
    TextAppearance
    0.88
    messageInfo
    0.82
    ClCompile
    0.73
    DockStyle
    0.72
    ciences
    0.71
    ppies
    0.68
     crescent
    0.66
    asuring
    0.65
    atase
    0.63
    iac
    0.63
    Activations Density 0.115%

    No Known Activations