© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91923
    Prev
    Next
    INDEX
    Explanations

    was

    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
    GEBURTSDATUM
    -0.76
     ujednoznacz
    -0.71
     بيها
    -0.63
     مرئيه
    -0.62
    endforeach
    -0.60
    endphp
    -0.60
    >--}}
    -0.60
    lizes
    -0.58
    </thead>
    -0.58
    naturally
    -0.57
    POSITIVE LOGITS
     then
    0.84
    then
    0.57
     too
    0.57
    Hozzáférés
    0.56
     thought
    0.54
     still
    0.52
     feeling
    0.52
    semantics
    0.52
     Then
    0.52
     akan
    0.52
    Activations Density 0.004%

    No Known Activations