© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97573
    Prev
    Next
    INDEX
    Explanations

    consuming

    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
     consumes
    -1.20
     consume
    -0.93
     consuming
    -0.85
    consuming
    -0.71
     requires
    -0.67
    DotNetBar
    -0.64
     consumed
    -0.63
     Requires
    -0.63
     consumir
    -0.60
     antaranya
    -0.60
    POSITIVE LOGITS
    ly
    0.82
     a
    0.70
    er
    0.67
    able
    0.65
     the
    0.64
     fresh
    0.57
    ably
    0.56
    ERTS
    0.56
    age
    0.55
    o
    0.54
    Activations Density 0.249%

    No Known Activations