© 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. 93787
    Prev
    Next
    INDEX
    Explanations

    code/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
    ACK
    -0.78
    hack
    -0.73
    acker
    -0.66
    acks
    -0.59
    ACKS
    -0.53
     con
    -0.52
     hack
    -0.50
    ck
    -0.48
    hacks
    -0.48
    ack
    -0.45
    POSITIVE LOGITS
     Monfieur
    0.97
     Majefty
    0.97
     raiſ
    0.93
     Diſ
    0.90
     purpoſe
    0.90
    ſelves
    0.89
     ſta
    0.88
     Jefus
    0.87
     pleaſure
    0.87
    ſelf
    0.86
    Activations Density 1.613%

    No Known Activations