© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3727
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
     doInBackground
    -0.61
     setuptools
    -0.54
     @"/
    -0.53
    mappedBy
    -0.50
    ="@+
    -0.50
     createContext
    -0.48
    Einzelnachweise
    -0.48
     initWithFrame
    -0.47
     useNavigate
    -0.47
    ValueGenerated
    -0.46
    POSITIVE LOGITS
    tvguidetime
    0.67
    alous
    0.62
    
    0.61
    :✨
    0.59
     Lightboxes
    0.57
    бливості
    0.55
     Unito
    0.55
    Personensuche
    0.54
     utafitiHapana
    0.54
    )++;
    0.54
    Activations Density 0.101%

    No Known Activations