© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96809
    Prev
    Next
    INDEX
    Explanations

    website snippets

    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
     mourut
    -0.65
    EndInit
    -0.65
     Normdatei
    -0.64
    MigrationBuilder
    -0.63
     zijne
    -0.60
    ьаж
    -0.59
    Хьажоргаш
    -0.59
    RenderAtEndOf
    -0.59
     fermée
    -0.58
     vocale
    -0.58
    POSITIVE LOGITS
    脚注の使い方
    0.55
    TagMode
    0.54
    emm
    0.52
    GraphicsUnit
    0.52
     typelib
    0.50
    homa
    0.50
     bagi
    0.49
    inephrine
    0.49
     gama
    0.49
     Unit
    0.49
    Activations Density 0.064%

    No Known Activations