© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43286
    Prev
    Next
    INDEX
    Explanations

    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
    -0.78
     Trust
    -0.67
     TRUST
    -0.63
    Trust
    -0.62
     Trusts
    -0.57
    trust
    -0.52
    ITY
    -0.49
    inds
    -0.47
     trust
    -0.47
    Estate
    -0.46
    POSITIVE LOGITS
    s
    1.09
    ی
    0.93
     AppColors
    0.81
    ship
    0.76
    e
    0.71
    sal
    0.71
    y
    0.69
    ing
    0.68
    salt
    0.68
     بيها
    0.68
    Activations Density 0.249%

    No Known Activations