© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73586
    Prev
    Next
    INDEX
    Explanations

    technical/scientific reports

    np_max-act-logits · 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
     saites
    -0.52
    cilis
    -0.47
     filtered
    -0.47
     filter
    -0.47
     caminhos
    -0.46
     HasFactory
    -0.45
     verlie
    -0.45
     väg
    -0.44
     Rup
    -0.44
    érons
    -0.44
    POSITIVE LOGITS
     headed
    0.70
     heads
    0.62
    ConstraintMaker
    0.59
    iastes
    0.59
    heads
    0.56
    headed
    0.56
     Heads
    0.54
     kaarangay
    0.54
    Head
    0.54
    RegressionTest
    0.54
    Activations Density 0.001%

    No Known Activations