© 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. 5-CLT-HP
    7. 93867
    Prev
    Next
    INDEX
    Explanations

    peace

    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
    참고
    -0.53
    ptor
    -0.51
    yr
    -0.49
    sia
    -0.47
    len
    -0.47
    unia
    -0.46
    idia
    -0.46
    yu
    -0.46
    VersionUID
    -0.45
    yp
    -0.45
    POSITIVE LOGITS
     resourceCulture
    0.73
    UnusedPrivate
    0.72
    SharedCtor
    0.68
     nahilalakip
    0.65
     againſt
    0.61
     IndexPath
    0.60
    InjectAttribute
    0.60
     AppCompatTheme
    0.60
    parsedMessage
    0.58
     '\\;'
    0.56
    Activations Density 0.000%

    No Known Activations