© 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. 40987
    Prev
    Next
    INDEX
    Explanations

    conditioning

    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
    IndentedString
    -0.69
    Jeografia
    -0.62
    programs
    -0.59
    FundMe
    -0.59
     autorytatywna
    -0.58
    kloped
    -0.58
     Samaria
    -0.57
     Vikipedi
    -0.57
    Programs
    -0.56
    Personensuche
    -0.56
    POSITIVE LOGITS
    Hochspringen
    0.50
     control
    0.49
    Izvori
    0.48
    apache
    0.47
    )\}$
    0.47
     domínio
    0.46
    occasione
    0.46
     rôles
    0.46
     diku
    0.45
    اقل
    0.45
    Activations Density 0.576%

    No Known Activations