© 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. 92225
    Prev
    Next
    INDEX
    Explanations

    is

    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
     stället
    -1.02
     itſelf
    -0.93
     varandra
    -0.92
    UVWXYZ
    -0.89
     purpoſe
    -0.88
     pleaſure
    -0.87
    ILDREN
    -0.83
     Normdatei
    -0.83
     fevere
    -0.82
    cessite
    -0.81
    POSITIVE LOGITS
    .
    0.69
    ↵
    0.68
    :
    0.63
    0.57
    !
    0.57
    ok
    0.57
    ↵↵↵
    0.56
    <h2>
    0.55
    ...
    0.54
    s
    0.53
    Activations Density 0.052%

    No Known Activations