© 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. 5-CLT-HP
    7. 94852
    Prev
    Next
    INDEX
    Explanations

    detail

    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
    TagMode
    -0.63
     doInBackground
    -0.63
    mergeFrom
    -0.63
     Vikipedi
    -0.61
    новништво
    -0.60
    Tembelea
    -0.60
    RectangleBorder
    -0.60
    DoubleQuotes
    -0.59
    GenerationType
    -0.57
    BASEPATH
    -0.57
    POSITIVE LOGITS
     phen
    0.61
    shortName
    0.49
    enschein
    0.48
    Phen
    0.46
     mut
    0.46
     rato
    0.46
     phenotypic
    0.44
    Lieber
    0.43
     character
    0.42
    phen
    0.42
    Activations Density 0.003%

    No Known Activations