© 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. 40638
    Prev
    Next
    INDEX
    Explanations

    technical/scientific writings

    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
    parsedMessage
    -0.60
    ada
    -0.57
    leasing
    -0.55
    able
    -0.54
    awtextra
    -0.54
    born
    -0.52
    łoż
    -0.51
    ador
    -0.50
    tainer
    -0.50
    adas
    -0.49
    POSITIVE LOGITS
    ніципа
    0.69
    mphony
    0.66
    yntaxException
    0.57
    complexContent
    0.54
    ffine
    0.52
    ITURE
    0.51
    insulin
    0.50
     médicas
    0.49
    ISupport
    0.48
    mpro
    0.47
    Activations Density 0.226%

    No Known Activations