© 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. 97737
    Prev
    Next
    INDEX
    Explanations

    any

    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
    any
    -2.00
    Any
    -1.94
     any
    -1.89
     Any
    -1.88
    ANY
    -1.83
     ANY
    -1.69
     qualquer
    -1.55
     cualquier
    -1.54
    Anything
    -1.53
     Anything
    -1.52
    POSITIVE LOGITS
     of
    0.99
     kind
    0.97
     sort
    0.80
     type
    0.79
     
    0.72
    how
    0.66
     form
    0.66
     thing
    0.64
     way
    0.63
     brand
    0.61
    Activations Density 0.038%

    No Known Activations