© 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. 5-CLT-HP
    7. 96682
    Prev
    Next
    INDEX
    Explanations

    d

    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
     be
    -1.10
     inject
    -0.85
     convert
    -0.84
     bake
    -0.83
     boil
    -0.81
     prosecute
    -0.81
     uſe
    -0.81
     fill
    -0.81
     isolate
    -0.80
     mark
    -0.79
    POSITIVE LOGITS
     vient
    0.53
    Entra
    0.50
    Become
    0.48
     viennent
    0.47
    HostException
    0.47
    windowFixed
    0.45
     spécialisée
    0.45
     freut
    0.44
    UnusedPrivate
    0.44
     rounds
    0.43
    Activations Density 0.016%

    No Known Activations