© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 90751
    Prev
    Next
    INDEX
    Explanations

    conducted

    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
     conducted
    -1.98
     conducting
    -1.80
    conducted
    -1.77
    Conduct
    -1.69
     conduct
    -1.64
     conducts
    -1.63
     Conducted
    -1.60
     Conducting
    -1.59
    conducting
    -1.49
     Conduct
    -1.48
    POSITIVE LOGITS
    sing
    0.55
     kasarigan
    0.55
     Bayard
    0.55
     amortization
    0.54
     annuities
    0.54
     mercies
    0.53
     amnesia
    0.53
     finesse
    0.53
     amnesty
    0.52
     subtlety
    0.52
    Activations Density 0.046%

    No Known Activations