© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 13543
    Prev
    Next
    INDEX
    Explanations

    Random

    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
    Random
    -0.85
     Random
    -0.63
     RANDOM
    -0.42
    ark
    -0.40
     randomly
    -0.40
    bitField
    -0.39
    б
    -0.39
     Congress
    -0.38
    DatabaseError
    -0.38
    random
    -0.37
    POSITIVE LOGITS
    ly
    1.50
    LY
    1.18
    ized
    1.16
    ised
    1.09
    ization
    1.08
    ness
    1.05
    selves
    0.91
    theless
    0.90
    neath
    0.89
    tened
    0.84
    Activations Density 0.004%

    No Known Activations