© 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. 41988
    Prev
    Next
    INDEX
    Explanations

    DU

    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
    DU
    -0.78
    tides
    -0.65
     Conſ
    -0.65
     Houſe
    -0.65
     Monfieur
    -0.62
     Reſ
    -0.60
     död
    -0.59
     Chriftian
    -0.58
    lewati
    -0.57
     Anſ
    -0.57
    POSITIVE LOGITS
     оригіналу
    0.73
    parsedMessage
    0.66
    DockStyle
    0.59
     nakalista
    0.58
    帖最后由
    0.57
    Tikang
    0.57
    MessageOf
    0.56
    الحياه
    0.55
     defaultstate
    0.55
    mentaux
    0.54
    Activations Density 0.120%

    No Known Activations