© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42018
    Prev
    Next
    INDEX
    Explanations

    assurance/trust

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trust
    -1.50
     trusting
    -1.34
     assumption
    -1.31
    trust
    -1.21
     presumption
    -1.19
     confidence
    -1.15
     fiducia
    -1.13
    assumption
    -1.12
     TRUST
    -1.09
     confiance
    -1.08
    POSITIVE LOGITS
     ca
    0.59
     or
    0.57
     and
    0.56
    ment
    0.52
     about
    0.52
     of
    0.51
     from
    0.49
    UpInside
    0.48
     set
    0.47
     cap
    0.47
    Activations Density 0.086%

    No Known Activations