© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 39987
    Prev
    Next
    INDEX
    Explanations

    eating

    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
     eaten
    -2.02
     ingested
    -1.95
     consumed
    -1.91
     swallowed
    -1.53
     devoured
    -1.52
    consumed
    -1.48
     avoient
    -1.47
     auroit
    -1.47
     feroit
    -1.41
     absorbed
    -1.36
    POSITIVE LOGITS
     by
    0.84
     
    0.82
     a
    0.72
     pre
    0.70
     en
    0.69
     in
    0.67
     '
    0.66
     de
    0.66
     an
    0.65
     sur
    0.65
    Activations Density 0.088%

    No Known Activations