© 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. 1-CLT-HP
    7. 11891
    Prev
    Next
    INDEX
    Explanations

    about

    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
    Sucesor
    -0.60
     tartalomajánló
    -0.55
    Rhestr
    -0.55
     esternos
    -0.54
    Separate
    -0.54
     ModelExpression
    -0.52
     setuptools
    -0.52
    TypedDataSet
    -0.52
     تضيفلها
    -0.51
     canst
    -0.51
    POSITIVE LOGITS
     the
    0.87
     it
    0.66
     talking
    0.66
     taking
    0.63
     having
    0.61
     spending
    0.61
     letting
    0.61
     trying
    0.59
     putting
    0.58
     those
    0.58
    Activations Density 0.485%

    No Known Activations