© 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. 40936
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    of

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     of
    -1.73
     löyty
    -0.80
     vectorielles
    -0.78
     laikā
    -0.73
     refusé
    -0.70
     igång
    -0.70
     aikana
    -0.70
     väli
    -0.69
     ferons
    -0.69
     της
    -0.69
    POSITIVE LOGITS
     the
    1.17
     your
    0.94
     a
    0.93
     our
    0.89
     an
    0.87
     my
    0.78
     this
    0.75
     his
    0.73
     any
    0.73
     course
    0.72
    Activations Density 1.966%

    No Known Activations