© 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. 5-CLT-HP
    7. 5227
    Prev
    Next
    INDEX
    Explanations

    Doctor, appeals, legal documents

    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
    JvmStatic
    -0.60
    findpost
    -0.56
    ScopeManager
    -0.56
    Fordítás
    -0.52
     protoimpl
    -0.52
     nahilalakip
    -0.52
    migrationBuilder
    -0.52
    SdkVersion
    -0.50
    Зноскі
    -0.50
    azgo
    -0.49
    POSITIVE LOGITS
    .
    0.65
     surla
    0.52
    .$.
    0.47
     Polonia
    0.47
    .«
    0.46
     belli
    0.46
     velour
    0.45
     sedentary
    0.45
    $.
    0.45
     geomet
    0.45
    Activations Density 0.006%

    No Known Activations