© 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. 72611
    Prev
    Next
    INDEX
    Explanations

    dra

    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
    addCriterion
    -0.54
    posedge
    -0.53
     ModelAndView
    -0.53
     الرياضيه
    -0.50
     venons
    -0.47
    AntiForgeryToken
    -0.44
    astify
    -0.41
    oredCriteria
    -0.41
     WaitForSeconds
    -0.41
    govina
    -0.41
    POSITIVE LOGITS
    esgue
    0.60
     ujednoznacz
    0.57
    phère
    0.57
    artige
    0.57
     ball
    0.56
    findpost
    0.56
     Paus
    0.55
    ball
    0.55
    red
    0.54
     Athene
    0.54
    Activations Density 0.003%

    No Known Activations