© 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. 41256
    Prev
    Next
    INDEX
    Explanations

    media origins

    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
     radio
    -1.07
     Radio
    -0.75
     ra
    -0.75
    radio
    -0.73
     RADIO
    -0.69
     radios
    -0.65
     радио
    -0.65
    Radio
    -0.58
     carried
    -0.57
    RADIO
    -0.57
    POSITIVE LOGITS
    AccessorTable
    0.82
     uș
    0.66
    rungsseite
    0.63
     فريبيس
    0.61
    PRNewswire
    0.61
    +#+#
    0.60
     propOrder
    0.58
     ſtate
    0.56
    UALA
    0.54
     חיצוניים
    0.54
    Activations Density 0.229%

    No Known Activations