© 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. 77593
    Prev
    Next
    INDEX
    Explanations

    chronic

    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
    onAttach
    -0.79
     дописавши
    -0.75
    rungsseite
    -0.74
    WebVitals
    -0.73
     '\\;'
    -0.62
     propOrder
    -0.62
    Rüyada
    -0.58
     المعيارى
    -0.58
    contentLoaded
    -0.58
     Meksiku
    -0.58
    POSITIVE LOGITS
    RuntimeObject
    0.49
     بلکه
    0.48
    ینده
    0.46
     quoi
    0.45
    ところで
    0.44
    noční
    0.44
     Normdatei
    0.44
     Suprema
    0.44
    lla
    0.44
     Syllabus
    0.43
    Activations Density 0.004%

    No Known Activations