© 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. 20-CLT-HP
    7. 72797
    Prev
    Next
    INDEX
    Explanations

    language fragments and misspellings

    np_max-act-logits · 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
    شهاد
    -0.69
    脚注の使い方
    -0.65
    protoimpl
    -0.64
    Kaynakça
    -0.63
     déchir
    -0.63
    曖昧さ回避
    -0.61
    RegistryLite
    -0.60
     DBNull
    -0.60
    drawSprites
    -0.59
    ioutil
    -0.59
    POSITIVE LOGITS
    ogan
    0.45
    oog
    0.45
     GEOLOGY
    0.43
     الرياضيه
    0.41
    oga
    0.41
    OkHttpClient
    0.40
    وح
    0.40
    othea
    0.40
    ogen
    0.40
     Sue
    0.40
    Activations Density 0.002%

    No Known Activations