© 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. 9690
    Prev
    Next
    INDEX
    Explanations

    not

    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
     had
    -0.94
     differed
    -0.85
    Had
    -0.82
     belonged
    -0.82
    had
    -0.82
     was
    -0.80
     were
    -0.78
    grew
    -0.78
     resembled
    -0.77
    seemed
    -0.77
    POSITIVE LOGITS
     previously
    0.79
     able
    0.71
     originally
    0.70
     born
    0.66
     autrefois
    0.63
     formerly
    0.62
    Życiorys
    0.60
     successful
    0.60
     initially
    0.57
     taken
    0.57
    Activations Density 0.076%

    No Known Activations