© 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. 2-RES-MATRYOSHKA-DC
    7. 3590
    Prev
    Next
    INDEX
    Explanations

    references or mentions of specific tools

    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
    Method
    -1.11
     Method
    -1.09
     method
    -1.06
     METHOD
    -1.04
    methods
    -1.03
    method
    -1.00
     Método
    -1.00
    Método
    -0.99
     Methods
    -0.98
     methods
    -0.96
    POSITIVE LOGITS
     tool
    3.06
     tools
    3.00
     Tool
    2.89
     Tools
    2.88
    tool
    2.78
    tools
    2.75
    Tool
    2.72
    Tools
    2.63
     TOOL
    2.61
     TOOLS
    2.61
    Activations Density 0.037%

    No Known Activations