© 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. 4-CLT-HP
    7. 2920
    Prev
    Next
    INDEX
    Explanations

    code and licenses

    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
    kezett
    -0.48
     imageNamed
    -0.48
    haar
    -0.46
     discontinuity
    -0.45
    hors
    -0.44
    érard
    -0.43
     sopp
    -0.43
     RDS
    -0.42
    opus
    -0.42
    __((
    -0.42
    POSITIVE LOGITS
    complexContent
    0.67
    UserScript
    0.65
     سكانية
    0.63
    RTLD
    0.60
    Personendaten
    0.59
     FetchType
    0.58
    WebVitals
    0.58
     Skin
    0.57
    ConstraintMaker
    0.56
    tanleria
    0.55
    Activations Density 0.018%

    No Known Activations