© 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. 92196
    Prev
    Next
    INDEX
    Explanations

    enter

    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
     enter
    -1.45
     add
    -0.96
    enter
    -0.66
     Enter
    -0.61
     go
    -0.54
    Enter
    -0.50
     Add
    -0.48
     enters
    -0.47
    enteric
    -0.47
     toute
    -0.46
    POSITIVE LOGITS
     purpoſe
    1.13
     Monfieur
    1.11
     ſmall
    1.08
     poffible
    1.08
     faſt
    1.05
     ſtre
    1.04
     ſta
    1.04
     pleaſure
    1.04
     houſe
    1.02
     Jefus
    1.02
    Activations Density 0.037%

    No Known Activations