© 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. 1-CLT-HP
    7. 13479
    Prev
    Next
    INDEX
    Explanations

    code/abbreviations

    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
    Portály
    -0.64
    ValueStyle
    -0.52
    WebElementEntity
    -0.50
     Leh
    -0.46
    scanf
    -0.45
    écart
    -0.45
     bloem
    -0.45
    胱
    -0.45
    ülé
    -0.45
     BorderRadius
    -0.44
    POSITIVE LOGITS
    ⓧ
    0.58
     betweenstory
    0.57
    ous
    0.57
    itier
    0.56
    BackStack
    0.55
    aried
    0.52
    principalTable
    0.52
     يتيمه
    0.52
    VersionUID
    0.52
    UnusedPrivate
    0.52
    Activations Density 0.079%

    No Known Activations