© 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. 4-CLT-HP
    7. 456
    Prev
    Next
    INDEX
    Explanations

    scientific measurements and data

    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
    .
    -0.47
    something
    -0.40
    الإنجليزية
    -0.39
     intermittently
    -0.39
    horabuena
    -0.37
    Something
    -0.37
     فريبيس
    -0.37
     Something
    -0.36
    Portail
    -0.36
     augus
    -0.35
    POSITIVE LOGITS
    BeginContext
    0.77
    RegistryLite
    0.71
    Gweler
    0.67
    jsxFileName
    0.64
    AutoScaleMode
    0.61
    YOND
    0.61
    createCanvas
    0.61
    PreferredItem
    0.61
    GEBURTSDATUM
    0.60
    commodations
    0.60
    Activations Density 0.002%

    No Known Activations