© 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. 97200
    Prev
    Next
    INDEX
    Explanations

    can

    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
     can
    -1.24
     Can
    -0.80
     können
    -0.77
    出版年
    -0.77
    can
    -0.75
    Can
    -0.73
     pouvez
    -0.73
    ThroughAttribute
    -0.69
    الدراسه
    -0.68
     CAN
    -0.68
    POSITIVE LOGITS
    opies
    0.76
    '
    0.73
    "
    0.69
     be
    0.69
    ’
    0.56
     nime
    0.55
     significantly
    0.54
     accommodate
    0.51
     dramatically
    0.50
    “
    0.50
    Activations Density 0.021%

    No Known Activations