© 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. 3747
    Prev
    Next
    INDEX
    Explanations

    mail

    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
     pitié
    -0.58
    bootstrapcdn
    -0.57
     ainfi
    -0.55
     bonté
    -0.54
     végét
    -0.52
     hâte
    -0.52
     dépenses
    -0.51
    出版年
    -0.51
     VizieR
    -0.50
     réguli
    -0.50
    POSITIVE LOGITS
    TestingModule
    0.55
    -
    0.54
    })));
    0.46
    ruitment
    0.46
    HasAnnotation
    0.46
    iprot
    0.45
    SuppressMessage
    0.43
    INSIDE
    0.42
    Numerology
    0.42
    rungsseite
    0.42
    Activations Density 0.001%

    No Known Activations