© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2488
    Prev
    Next
    INDEX
    Explanations

    steroids and medical treatments

    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
     بيها
    -0.79
    SourceChecksum
    -0.71
    +#+#
    -0.68
    WaitGroup
    -0.65
    enumi
    -0.65
    +:+
    -0.63
    rinfo
    -0.63
     kasarigan
    -0.62
    enumii
    -0.61
     发表于
    -0.60
    POSITIVE LOGITS
    IonicModule
    0.51
    Respectfully
    0.44
     Aro
    0.44
    Son
    0.43
    alternate
    0.42
     dip
    0.42
     Lath
    0.42
    asson
    0.42
     الاس
    0.42
    Shotgun
    0.41
    Activations Density 0.006%

    No Known Activations