© 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. 1-RES-MATRYOSHKA-DC
    7. 964
    Prev
    Next
    INDEX
    Explanations

    explanations regarding definitions or clarifications

    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
     cauza
    -0.68
    due
    -0.65
     devido
    -0.65
     oprot
    -0.65
     cause
    -0.62
     CAUSE
    -0.62
     due
    -0.61
    cause
    -0.60
    ChildScrollView
    -0.60
     DUE
    -0.60
    POSITIVE LOGITS
     means
    4.34
    means
    4.06
     Means
    4.00
    Means
    3.91
     MEANS
    3.72
     mean
    2.89
     meant
    2.56
    mean
    2.42
     Mean
    2.42
     MEAN
    2.42
    Activations Density 0.338%

    No Known Activations