© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41821
    Prev
    Next
    INDEX
    Explanations

    game

    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
    InjectAttribute
    -1.00
     ostavi
    -0.98
    NameInMap
    -0.96
    MessageOf
    -0.94
    出版年
    -0.91
     nakalista
    -0.91
     HasFactory
    -0.91
    ########.
    -0.89
     transfieras
    -0.88
     utafitiHapana
    -0.87
    POSITIVE LOGITS
    diğinde
    0.44
    s
    0.42
    safety
    0.41
    spricht
    0.40
    határoz
    0.38
    を果た
    0.36
    違います
    0.35
     a
    0.35
    ierta
    0.34
    plu
    0.34
    Activations Density 1.167%

    No Known Activations