© 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. 4605
    Prev
    Next
    INDEX
    Explanations

    Time (years, anniversary)

    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
    MouseButton
    -0.44
     câte
    -0.41
    Estat
    -0.41
    tuig
    -0.40
    omb
    -0.39
    querySelector
    -0.38
    woordig
    -0.38
    懸命
    -0.38
    bukkit
    -0.37
     campion
    -0.37
    POSITIVE LOGITS
    
    0.75
    endphp
    0.69
    ArrowToggle
    0.65
     الحره
    0.63
     فريبيس
    0.61
    raulic
    0.60
    CPtr
    0.60
    ValueStyle
    0.59
    ">—
    0.58
    enumi
    0.58
    Activations Density 0.003%

    No Known Activations