© 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. 4-CLT-HP
    7. 1016
    Prev
    Next
    INDEX
    Explanations

    notice

    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
     funny
    -0.45
     gods
    -0.44
     nutricional
    -0.41
     Ncert
    -0.41
     immoral
    -0.41
     carp
    -0.41
     smoky
    -0.41
    ترم
    -0.41
     Custer
    -0.40
     Smoky
    -0.40
    POSITIVE LOGITS
     pinulongan
    0.76
    rungsseite
    0.71
    UnusedPrivate
    0.68
     <>",
    0.67
    intahan
    0.61
    ThroughAttribute
    0.60
     relâche
    0.60
    buttonBar
    0.60
    delwed
    0.59
    XmlEnum
    0.59
    Activations Density 0.002%

    No Known Activations