© 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. 0-CLT-HP
    4. 1471
    Prev
    Next
    INDEX
    Explanations

    dangers or risks

    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
     pose
    -2.23
     poses
    -2.09
     posed
    -2.06
     posing
    -1.93
     Pose
    -1.87
    pose
    -1.56
     Pos
    -1.52
    poses
    -1.50
    Pose
    -1.47
    posed
    -1.42
    POSITIVE LOGITS
     Dumnezeu
    0.66
     femeninos
    0.65
     Jefus
    0.64
     piele
    0.63
     ſte
    0.62
    醐
    0.62
     coreana
    0.61
     Monfieur
    0.60
     تانيه
    0.60
     Espanha
    0.60
    Activations Density 0.155%

    No Known Activations