© 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. 93550
    Prev
    Next
    INDEX
    Explanations

    users

    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
     user
    -1.42
     users
    -1.39
     of
    -1.33
     User
    -1.20
     Users
    -1.16
    user
    -1.13
    users
    -1.03
    User
    -0.98
    Users
    -0.94
    USER
    -0.91
    POSITIVE LOGITS
     تضيفلها
    0.89
     Réponses
    0.88
     محفوظة
    0.80
    Geplaatst
    0.74
    UnsafeEnabled
    0.74
    lihood
    0.71
    ValueStyle
    0.71
    gemene
    0.67
    TagMode
    0.66
     ویکی‌پدیای
    0.66
    Activations Density 0.143%

    No Known Activations