© 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. 93575
    Prev
    Next
    INDEX
    Explanations

    6

    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
     secs
    -0.54
    tamol
    -0.51
     washable
    -0.50
    ielli
    -0.49
     Jovi
    -0.48
     IFS
    -0.48
     lions
    -0.47
    passive
    -0.47
     crus
    -0.46
     Washable
    -0.46
    POSITIVE LOGITS
    AndroidJUnit
    0.95
    تقاوى
    0.79
    HasAnnotation
    0.74
    ExtendWith
    0.74
    RTEX
    0.69
    awaiter
    0.69
    (!__
    0.68
    WithMany
    0.67
    AsUp
    0.67
    Personendaten
    0.66
    Activations Density 0.003%

    No Known Activations