© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 90505
    Prev
    Next
    INDEX
    Explanations

    dep

    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
    #
    -0.69
    e
    -0.63
    a
    -0.59
    //
    -0.56
    ा
    -0.54
    o
    -0.52
    sted
    -0.52
    sk
    -0.51
     poveznice
    -0.50
    erweise
    -0.50
    POSITIVE LOGITS
    oneofs
    0.64
    SourceChecksum
    0.57
     reindeer
    0.57
     Egli
    0.57
    ors
    0.56
    ISupport
    0.56
     swans
    0.54
     незавершена
    0.54
     offending
    0.53
    ſelf
    0.53
    Activations Density 0.057%

    No Known Activations