© 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. 736
    Prev
    Next
    INDEX
    Explanations

    the phrase "a computational model" or similar descriptions of "an essential modeling tool" in text

    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
     therapy
    -2.50
     Therapy
    -2.36
    therapy
    -2.19
    Therapy
    -2.19
     THERAPY
    -2.11
     therapies
    -1.95
     Therapies
    -1.78
     therapeutic
    -1.77
     terapia
    -1.67
     therapists
    -1.65
    POSITIVE LOGITS
     tool
    2.91
     tools
    2.78
     Tool
    2.70
     Tools
    2.69
    tool
    2.58
    tools
    2.50
    Tool
    2.47
    Tools
    2.42
     TOOL
    2.39
     TOOLS
    2.31
    Activations Density 0.097%

    No Known Activations