© 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. 4-CLT-HP
    7. 2684
    Prev
    Next
    INDEX
    Explanations

    Referencing documents

    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
    St
    -0.53
    int
    -0.52
    J
    -0.52
    j
    -0.50
    <bos>
    -0.50
    Mr
    -0.49
    Ms
    -0.48
    H
    -0.47
    See
    -0.46
     ovale
    -0.46
    POSITIVE LOGITS
     المعيارى
    0.75
     оригіналу
    0.73
    AllAfrica
    0.66
    Cordialement
    0.66
    Autoritní
    0.66
    ReusableCell
    0.65
    Nhưng
    0.65
    virons
    0.64
     AssemblyCompany
    0.63
    enseignements
    0.63
    Activations Density 0.017%

    No Known Activations