© 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. 4-CLT-HP
    7. 1156
    Prev
    Next
    INDEX
    Explanations

    publication metadata

    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
    تقاوى
    -0.78
    Personendaten
    -0.76
     referenties
    -0.73
     Савезне
    -0.73
    tonsoft
    -0.71
     nahilalakip
    -0.71
    TRAILING
    -0.69
    }{*}{}
    -0.69
     unknownFields
    -0.68
    脚注の使い方
    -0.65
    POSITIVE LOGITS
    AnchorTagHelper
    0.45
    Personensuche
    0.45
    mybatisplus
    0.41
    inander
    0.41
    dep
    0.41
     compétence
    0.39
    endlich
    0.39
     hermanos
    0.38
     sociaux
    0.38
     poveznice
    0.38
    Activations Density 0.001%

    No Known Activations