© 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. 3-RES-MATRYOSHKA-DC
    7. 1986
    Prev
    Next
    INDEX
    Explanations

    the word "trust" and related words

    oai_token-act-pair · gemini-2.0-flash
    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
     pregă
    -0.70
     Koz
    -0.69
    SceneManagement
    -0.69
    EnableWeb
    -0.68
    WriteLiteral
    -0.68
     Bout
    -0.67
    Appender
    -0.67
     Insee
    -0.66
    醐
    -0.66
     Cabbage
    -0.66
    POSITIVE LOGITS
     trust
    3.11
     Trust
    2.86
    Trust
    2.86
    trust
    2.78
     trusts
    2.69
     TRUST
    2.67
    TRUST
    2.55
     trusting
    2.31
     Trusts
    2.28
     trusted
    2.20
    Activations Density 0.474%

    No Known Activations