© 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. 20-CLT-HP
    7. 73135
    Prev
    Next
    INDEX
    Explanations

    code, business descriptions

    np_max-act-logits · 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
    MENAFN
    -0.72
     consultato
    -0.64
     intptr
    -0.60
     whoſe
    -0.58
    Abitanti
    -0.56
     ControllerBase
    -0.56
     selecting
    -0.55
     localObject
    -0.54
    Portail
    -0.54
    protoc
    -0.54
    POSITIVE LOGITS
     للمعارف
    0.57
     show
    0.57
     shows
    0.47
    ğraf
    0.47
     Show
    0.45
    show
    0.45
    winds
    0.44
     drops
    0.44
     exist
    0.44
    cestershire
    0.43
    Activations Density 0.009%

    No Known Activations