© 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. 45136
    Prev
    Next
    INDEX
    Explanations

    innovation

    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
    StoryboardSegue
    -1.09
    sizeCache
    -0.97
     AttributeSet
    -0.93
    WebVitals
    -0.93
    ientôt
    -0.92
    parsedMessage
    -0.92
    writeFieldEnd
    -0.86
    ioneers
    -0.83
     >=",
    -0.83
     <>",
    -0.82
    POSITIVE LOGITS
    age
    0.71
    able
    0.63
    ous
    0.57
    am
    0.55
    ability
    0.54
    ages
    0.52
    ice
    0.52
    ac
    0.51
    ate
    0.51
    ador
    0.50
    Activations Density 0.049%

    No Known Activations