© 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. 92998
    Prev
    Next
    INDEX
    Explanations

    climate, programming, 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
     مرئيه
    -0.85
    .*")]
    -0.78
    
    -0.75
    featureID
    -0.73
     ujednoznacz
    -0.71
     AssemblyCulture
    -0.70
     Wikimedijinoj
    -0.66
    ThroughAttribute
    -0.66
    
    -0.66
     AspNetCore
    -0.65
    POSITIVE LOGITS
    󠁴
    0.47
     optimum
    0.45
    äd
    0.44
    Honorable
    0.42
    Kontrola
    0.42
    thylene
    0.41
     remarquer
    0.41
     pulls
    0.41
     tritium
    0.41
    zellan
    0.41
    Activations Density 0.001%

    No Known Activations