© 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. 92844
    Prev
    Next
    INDEX
    Explanations

    guilt, pointed

    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
     guilt
    -1.51
     Guilt
    -1.11
     pointed
    -0.91
     guilty
    -0.82
    pointed
    -0.77
    difficulty
    -0.76
    Informed
    -0.75
    guilty
    -0.75
     innocence
    -0.71
     informed
    -0.70
    POSITIVE LOGITS
    ly
    0.69
    ness
    0.61
    lessly
    0.54
    iness
    0.53
     disambiguazione
    0.51
    re
    0.50
    less
    0.50
    stood
    0.48
    pins
    0.48
    IUrlHelper
    0.48
    Activations Density 0.167%

    No Known Activations