© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94879
    Prev
    Next
    INDEX
    Explanations

    of

    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
    ">//
    -0.66
    verwijspagina
    -0.61
    selaer
    -0.60
    didSet
    -0.60
    jgl
    -0.59
     Whiting
    -0.59
     Carriers
    -0.58
    Hozzáférés
    -0.58
    onicus
    -0.56
    valve
    -0.56
    POSITIVE LOGITS
    InputBorder
    0.53
    ContentAsync
    0.53
    createCell
    0.47
    ➞
    0.46
     Gedächt
    0.44
     initComponents
    0.44
    jsxFileName
    0.43
    SUCCESS
    0.42
    (?)
    0.42
    NOPQRST
    0.41
    Activations Density 0.005%

    No Known Activations