© 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. 585
    Prev
    Next
    INDEX
    Explanations

    references to the support or endorsement of a particular entity or activity

    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
     helps
    -0.56
     helped
    -0.52
    Helps
    -0.50
    printStackTrace
    -0.49
    helped
    -0.49
     Fleming
    -0.49
     Helps
    -0.48
     MediatR
    -0.47
     hilft
    -0.47
     helping
    -0.47
    POSITIVE LOGITS
     support
    4.31
     Support
    4.09
    support
    4.09
    Support
    4.03
     SUPPORT
    3.75
    SUPPORT
    3.53
     supports
    3.52
     Supports
    3.31
     supported
    3.25
     supporting
    3.23
    Activations Density 0.224%

    No Known Activations