© 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. 4-CLT-HP
    7. 958
    Prev
    Next
    INDEX
    Explanations

    "of"

    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
     a
    -0.60
     an
    -0.56
     бя
    -0.50
     not
    -0.44
    ')}}"
    -0.44
     blevet
    -0.43
    tvguidetime
    -0.43
     måske
    -0.42
     nasıl
    -0.42
     usually
    -0.40
    POSITIVE LOGITS
     ProtoMessage
    0.87
    ValueStyle
    0.75
    GEBURTSDATUM
    0.73
     to
    0.69
    DebuggerNonUser
    0.65
    webElementXpaths
    0.64
     initComponents
    0.63
    الحياه
    0.63
     Seeder
    0.63
    astéroïdes
    0.62
    Activations Density 0.005%

    No Known Activations