© 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. 1-CLT-HP
    7. 11357
    Prev
    Next
    INDEX
    Explanations

    software/programming

    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
    Quest
    -1.52
    QUEST
    -0.91
     QUEST
    -0.84
     Quest
    -0.78
    fjspx
    -0.72
     Roskov
    -0.71
     Quests
    -0.68
    quest
    -0.65
     خارجية
    -0.62
     quest
    -0.62
    POSITIVE LOGITS
    Према
    0.61
     LoggerFactory
    0.56
    bootstrapcdn
    0.52
    withstanding
    0.49
    netbeans
    0.49
    abank
    0.48
    íncia
    0.47
    AccessException
    0.47
    ExecuteNonQuery
    0.47
     appreciated
    0.46
    Activations Density 0.083%

    No Known Activations