© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 818
    Prev
    Next
    INDEX
    Explanations

    Academic text beginnings

    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
    DoubleQuotes
    -0.59
    SBATCH
    -0.58
    retto
    -0.57
    endwhile
    -0.55
    Искәрмәләр
    -0.54
    mares
    -0.54
    NOPQRST
    -0.54
     profitability
    -0.54
    nastics
    -0.53
    Anhalt
    -0.52
    POSITIVE LOGITS
    StoreMessageInfo
    0.56
    adpleegd
    0.55
    MigrationBuilder
    0.53
     téléchargez
    0.50
     and
    0.50
    Portail
    0.48
    +#+#
    0.47
    protoimpl
    0.47
    wakili
    0.46
     leçon
    0.46
    Activations Density 0.006%

    No Known Activations