© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9624
    Prev
    Next
    INDEX
    Explanations

    math

    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
    (!__
    -0.60
    poons
    -0.52
    __*/
    -0.52
     harps
    -0.50
    ophysical
    -0.50
     تضيفلها
    -0.49
    SourceChecksum
    -0.48
    󠁣
    -0.48
    Sklici
    -0.48
     consultato
    -0.48
    POSITIVE LOGITS
     CreateTagHelper
    0.86
    Carriera
    0.60
    InstanceState
    0.54
     AssemblyTitle
    0.54
    XmlAccessorType
    0.51
    <bos>
    0.50
    futbolista
    0.49
     disambiguazione
    0.48
    RouterModule
    0.48
    CompilerServices
    0.48
    Activations Density 0.003%

    No Known Activations