© 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. 5-CLT-HP
    7. 3917
    Prev
    Next
    INDEX
    Explanations

    Programming, code, technical topics

    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
    WebElementEntity
    -0.86
     surla
    -0.67
     doubtnut
    -0.66
    berdayakan
    -0.66
    !*\
    -0.64
     myſelf
    -0.62
    PostInfinity
    -0.61
     DriverManager
    -0.60
     تكبرها
    -0.60
    apimachinery
    -0.60
    POSITIVE LOGITS
     shock
    0.52
     rapid
    0.50
     protective
    0.49
     respiratory
    0.49
     shell
    0.45
     starvation
    0.45
    WRITER
    0.44
     tor
    0.43
     a
    0.42
     Protective
    0.42
    Activations Density 0.002%

    No Known Activations