© 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. 0-CLT-HP
    7. 92940
    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
    ’
    -0.59
     aikana
    -0.58
     laikā
    -0.58
    '
    -0.55
     délais
    -0.54
    <eos>
    -0.51
     mencionados
    -0.47
     pegatina
    -0.46
     diatas
    -0.46
     című
    -0.45
    POSITIVE LOGITS
     example
    1.10
     pleaſure
    1.08
     purpoſe
    1.07
     the
    1.00
     reaſon
    0.98
     Monfieur
    0.98
     ſtate
    0.97
     themſelves
    0.96
     ſeveral
    0.96
     instance
    0.96
    Activations Density 0.048%

    No Known Activations