© 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. 0-CLT-HP
    7. 94229
    Prev
    Next
    INDEX
    Explanations

    feelings/emotions

    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
    gens
    -0.61
    er
    -0.54
    mpa
    -0.47
    hasPermission
    -0.47
    вью
    -0.46
    ズの
    -0.45
    ed
    -0.44
    eria
    -0.44
    able
    -0.44
    nus
    -0.44
    POSITIVE LOGITS
     Normdatei
    0.86
    المناصب
    0.84
    AntiForgeryToken
    0.84
    findpost
    0.82
    enumi
    0.81
    帖最后由
    0.80
    ंदीखरीदारी
    0.76
     ostavi
    0.76
    postIndex
    0.73
     nakalista
    0.72
    Activations Density 0.038%

    No Known Activations