© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13832
    Prev
    Next
    INDEX
    Explanations

    for

    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
     us
    -0.79
     for
    -0.59
    <eos>
    -0.53
     me
    -0.52
     to
    -0.48
     him
    -0.47
    ↵
    -0.45
    WebElementEntity
    -0.45
    -
    -0.45
    GEBURTSDATUM
    -0.44
    POSITIVE LOGITS
     myſelf
    0.88
     reaſon
    0.87
     ་་
    0.85
     raiſ
    0.84
     cdti
    0.82
     pleaſure
    0.81
     deſt
    0.78
    __':
    0.78
     ſeveral
    0.78
     Reſ
    0.77
    Activations Density 0.123%

    No Known Activations