© 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. 0-CLT-HP
    7. 41944
    Prev
    Next
    INDEX
    Explanations

    ads

    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
     ad
    -2.05
     Ad
    -1.56
    Ad
    -1.45
     ads
    -1.44
    ad
    -1.34
     advertisement
    -1.30
     advertising
    -1.20
     advert
    -1.18
    ads
    -1.16
     advertisements
    -1.12
    POSITIVE LOGITS
     crdi
    0.85
     poffe
    0.74
     Efq
    0.70
     myſelf
    0.70
     itſelf
    0.68
     himſelf
    0.67
     doubtnut
    0.66
     scritta
    0.66
     Houſe
    0.65
    =$?
    0.64
    Activations Density 1.702%

    No Known Activations