© 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. 5-CLT-HP
    7. 91391
    Prev
    Next
    INDEX
    Explanations

    truth/actuality

    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
    AddTagHelper
    -0.59
    __(/*!
    -0.59
    TestingModule
    -0.58
    ukone
    -0.57
    GTCX
    -0.57
     للاسماء
    -0.53
    cipar
    -0.53
    Gön
    -0.52
    ัติ
    -0.51
     islas
    -0.51
    POSITIVE LOGITS
     that
    0.72
     realities
    0.71
     realistically
    0.59
     realistic
    0.56
    abestanden
    0.55
     reality
    0.54
     réaliste
    0.54
    ัจ
    0.53
     contextLoads
    0.52
    Reality
    0.52
    Activations Density 0.001%

    No Known Activations