© 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. 90590
    Prev
    Next
    INDEX
    Explanations

    Lymphocytes

    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
    Dislikes
    -0.58
     Bastard
    -0.57
     Orrell
    -0.55
     normaux
    -0.55
     kveld
    -0.54
    MessageOf
    -0.53
    JspWriter
    -0.52
    __':
    -0.51
    aragus
    -0.51
     indifference
    -0.50
    POSITIVE LOGITS
    MENAFN
    0.69
    BASEPATH
    0.63
    andoah
    0.56
    aat
    0.54
    hagic
    0.51
     >=",
    0.48
    AndEndTag
    0.47
    liceerd
    0.47
    ExecuteReader
    0.47
     kasarigan
    0.46
    Activations Density 0.072%

    No Known Activations