© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40961
    Prev
    Next
    INDEX
    Explanations

    other

    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
     a
    -0.83
     their
    -0.80
     the
    -0.77
     other
    -0.76
     outras
    -0.54
     it
    -0.53
     to
    -0.53
     another
    -0.52
    other
    -0.51
     Other
    -0.51
    POSITIVE LOGITS
     ―――――
    0.75
    ็จ
    0.72
    Tikang
    0.69
     שוליים
    0.67
     ་་
    0.67
     HOF
    0.67
     
    0.66
     OCS
    0.65
     itſelf
    0.65
     leſs
    0.64
    Activations Density 0.066%

    No Known Activations