© 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. 5-CLT-HP
    7. 92181
    Prev
    Next
    INDEX
    Explanations

    Internet/technical writing

    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
     that
    -0.67
    ,
    -0.59
     those
    -0.54
     this
    -0.53
    сятся
    -0.47
     it
    -0.47
     units
    -0.46
     participants
    -0.46
    手下
    -0.46
    ;
    -0.45
    POSITIVE LOGITS
     rêves
    0.62
     larmes
    0.62
     enfans
    0.62
     vérit
    0.61
     peines
    0.59
     varandra
    0.57
     skolan
    0.57
     colère
    0.57
     défauts
    0.56
     tombé
    0.56
    Activations Density 0.000%

    No Known Activations