© 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. 5-CLT-HP
    7. 92287
    Prev
    Next
    INDEX
    Explanations

    technical topics

    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
     bays
    -0.60
     markets
    -0.60
     voltages
    -0.59
     uș
    -0.59
     volumes
    -0.57
    banks
    -0.57
    markets
    -0.57
     Hände
    -0.57
    vehicles
    -0.56
    Markets
    -0.56
    POSITIVE LOGITS
    原始内容存档于
    0.69
    UnusedPrivate
    0.63
    twimg
    0.60
    Климат
    0.57
    DECREF
    0.57
    kloped
    0.56
    RTLD
    0.56
     simplifié
    0.56
    elemField
    0.54
     CreateTagHelper
    0.53
    Activations Density 0.004%

    No Known Activations