© 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. 4-CLT-HP
    7. 1988
    Prev
    Next
    INDEX
    Explanations

    rink

    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
     RoutedEventArgs
    -0.57
     []:
    -0.52
    EObject
    -0.51
     informée
    -0.47
    Hướng
    -0.46
     działal
    -0.45
    homonymie
    -0.45
    !\!\
    -0.44
    EXHIB
    -0.44
     Bucure
    -0.43
    POSITIVE LOGITS
    king
    0.60
    RUnlock
    0.59
    ning
    0.58
    ftagPool
    0.57
    ed
    0.56
    OGND
    0.55
     Plast
    0.54
    ier
    0.54
     فريبيس
    0.53
    driving
    0.52
    Activations Density 0.001%

    No Known Activations