© 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. 715
    Prev
    Next
    INDEX
    Explanations

    standard

    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
    anskje
    -0.56
    TagHelper
    -0.54
     fernández
    -0.53
     fumée
    -0.53
    utilisons
    -0.52
     gomma
    -0.52
     Command
    -0.52
     nahilalakip
    -0.52
     صوتيه
    -0.51
     *
    -0.51
    POSITIVE LOGITS
    NamedQueries
    0.61
    Personendaten
    0.58
    ByExample
    0.52
    ніципа
    0.51
    دانشنامهٔ
    0.50
     values
    0.50
    ipot
    0.47
    /***/
    0.47
    Spoljašnje
    0.47
    value
    0.46
    Activations Density 0.012%

    No Known Activations