© 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. 97983
    Prev
    Next
    INDEX
    Explanations

    dates

    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
     morning
    -0.52
    to
    -0.48
    第二天
    -0.43
     mañana
    -0.42
    (
    -0.42
     to
    -0.40
    '
    -0.39
    明日
    -0.39
     membrana
    -0.38
     matin
    -0.38
    POSITIVE LOGITS
    parsedMessage
    0.96
    findpost
    0.85
    spender
    0.85
    ✨:
    0.85
    tvguidetime
    0.79
    NUMX
    0.78
    writeFieldEnd
    0.78
     itſelf
    0.77
     resourceCulture
    0.76
    popularity
    0.75
    Activations Density 0.051%

    No Known Activations