© 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. 4-CLT-HP
    7. 2451
    Prev
    Next
    INDEX
    Explanations

    -

    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
     inject
    -0.70
     attach
    -0.69
     uſe
    -0.65
     affix
    -0.65
     detach
    -0.64
     deletes
    -0.63
     attaches
    -0.62
     fills
    -0.62
     bury
    -0.62
     selects
    -0.60
    POSITIVE LOGITS
     taken
    1.16
     gone
    0.97
     given
    0.96
    taken
    0.95
     eaten
    0.89
     gotten
    0.88
     risen
    0.85
     ridden
    0.85
     flown
    0.84
     broken
    0.81
    Activations Density 0.009%

    No Known Activations