© 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. 0-CLT-HP
    7. 90549
    Prev
    Next
    INDEX
    Explanations

    technology systems

    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
     متعلقه
    -1.22
     propOrder
    -1.21
    findpost
    -1.00
     disambiguazione
    -0.92
    rungsseite
    -0.88
     ujednoznacz
    -0.84
    IsMutable
    -0.83
     חיצוניים
    -0.83
     dAtA
    -0.82
    Personendaten
    -0.81
    POSITIVE LOGITS
     {}),
    0.52
     '/';
    0.50
     vox
    0.45
     agency
    0.45
     Denis
    0.45
     commentary
    0.44
     union
    0.44
     Vox
    0.43
     goods
    0.42
     stabilisation
    0.41
    Activations Density 0.084%

    No Known Activations