© 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. 96553
    Prev
    Next
    INDEX
    Explanations

    sufficient

    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
    URLException
    -0.79
     CURIAM
    -0.68
    存于互联网档案馆
    -0.67
    yntaxException
    -0.66
    Sufficient
    -0.66
     atleast
    -0.66
     reicht
    -0.66
    ReusableCell
    -0.66
     referenties
    -0.64
     createState
    -0.64
    POSITIVE LOGITS
     but
    0.72
     pero
    0.57
     tetapi
    0.50
    but
    0.50
     mais
    0.47
     jsPsych
    0.43
     بلکه
    0.43
     étions
    0.42
     tapi
    0.42
     une
    0.41
    Activations Density 0.002%

    No Known Activations