© 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. 4-CLT-HP
    4. 4927
    Prev
    Next
    INDEX
    Explanations

    affected

    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
    ///</
    -0.63
     mergeFrom
    -0.61
    naeus
    -0.58
    phrine
    -0.57
    :\/\/
    -0.56
     referenties
    -0.56
    ništ
    -0.56
    서는
    -0.56
    Comté
    -0.55
    TypedDataSet
    -0.54
    POSITIVE LOGITS
     ostavi
    0.63
     with
    0.62
    HasForeignKey
    0.57
     BufferedReader
    0.56
    EndContext
    0.56
    Становништво
    0.56
     delivered
    0.50
     afflicted
    0.49
    dyž
    0.49
     by
    0.48
    Activations Density 0.022%

    No Known Activations