© 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. 1-CLT-HP
    7. 10477
    Prev
    Next
    INDEX
    Explanations

    acquire

    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
    ReactDOM
    -0.54
    didSet
    -0.53
    Lähteet
    -0.52
    nonatomic
    -0.51
    Cyfeiriadau
    -0.48
    ))
    -0.47
    idopsis
    -0.47
    djangoproject
    -0.46
    urlpatterns
    -0.45
    consulté
    -0.45
    POSITIVE LOGITS
    EndInit
    0.63
     themſelves
    0.60
    mejores
    0.55
    ilisation
    0.55
     prisonniers
    0.54
     deschis
    0.53
    NUMX
    0.52
     Eſ
    0.52
     profondeur
    0.51
    parsedMessage
    0.51
    Activations Density 0.017%

    No Known Activations