© 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. 883
    Prev
    Next
    INDEX
    Explanations

    like/as

    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
     auszu
    -0.52
    หว่าง
    -0.50
     to
    -0.50
     mergeFrom
    -0.48
    randomUUID
    -0.46
     Taking
    -0.45
    XtraReports
    -0.45
    ImageContext
    -0.45
    stagland
    -0.44
    CodeAttribute
    -0.44
    POSITIVE LOGITS
    المناصب
    0.69
     how
    0.63
    جستارهای
    0.62
     ويكيميديا
    0.58
    how
    0.58
    بوابة
    0.57
    WebVitals
    0.55
    بالإنجليزية
    0.54
     AssemblyVersion
    0.53
    Παραπομπές
    0.53
    Activations Density 0.003%

    No Known Activations