© 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. 5-CLT-HP
    4. 94908
    Prev
    Next
    INDEX
    Explanations

    code

    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
     and
    -0.78
     but
    -0.72
     that
    -0.68
    and
    -0.64
     And
    -0.63
    <eos>
    -0.56
    that
    -0.55
     or
    -0.51
     if
    -0.49
     which
    -0.49
    POSITIVE LOGITS
    ISupport
    0.74
    Viitteet
    0.67
    RegressionTest
    0.66
    ConstraintMaker
    0.65
     Diſ
    0.64
    dotenv
    0.64
     Houſe
    0.64
     NavController
    0.63
     Shakspeare
    0.62
     houſe
    0.62
    Activations Density 0.008%

    No Known Activations