© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97147
    Prev
    Next
    INDEX
    Explanations

    filing

    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
     étoient
    -1.17
     étoit
    -1.15
     avoient
    -1.09
     feroit
    -1.07
     auroit
    -1.03
     habet
    -1.02
     pouvoit
    -1.01
     nôtre
    -0.90
     plufieurs
    -0.86
     ainfi
    -0.86
    POSITIVE LOGITS
     of
    0.75
    ,
    0.72
     a
    0.69
    able
    0.62
    <bos>
    0.62
     made
    0.58
    .
    0.57
    maker
    0.56
     the
    0.55
     «
    0.55
    Activations Density 0.073%

    No Known Activations