© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 71865
    Prev
    Next
    INDEX
    Explanations

    by

    np_max-act-logits · 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
    EndProject
    -0.69
    Brainz
    -0.65
    بوابة
    -0.64
    Portale
    -0.62
     referrerpolicy
    -0.60
    InjectAttribute
    -0.59
    WebElementEntity
    -0.57
    TargetException
    -0.56
    ########.
    -0.56
    
    -0.55
    POSITIVE LOGITS
     herb
    0.55
     udaler
    0.54
     sucking
    0.54
     piercing
    0.52
     glassy
    0.49
    twimg
    0.48
    iggio
    0.47
     ar
    0.47
     sap
    0.46
     monop
    0.46
    Activations Density 0.001%

    No Known Activations