© 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. 4-CLT-HP
    7. 882
    Prev
    Next
    INDEX
    Explanations

    varied discussions/support requests

    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
     supérieurs
    -0.75
     supérieures
    -0.75
     découver
    -0.70
     démocr
    -0.67
     indépend
    -0.67
     enfans
    -0.65
     faciles
    -0.64
    ResumeLayout
    -0.64
     récents
    -0.63
     présidenti
    -0.63
    POSITIVE LOGITS
     can
    0.89
     will
    0.87
     it
    0.85
     is
    0.84
     are
    0.76
     they
    0.70
     offers
    0.70
     the
    0.69
     make
    0.69
     would
    0.69
    Activations Density 0.006%

    No Known Activations