© 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. 91449
    Prev
    Next
    INDEX
    Explanations

    Job postings/University Information

    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
    хьтан
    -0.85
    EndTag
    -0.78
    دانشنامهٔ
    -0.74
     otomatig
    -0.72
     فريبيس
    -0.67
    =$?
    -0.66
    bootstrapcdn
    -0.66
    Насе
    -0.66
    PreferredItem
    -0.66
     crossorigin
    -0.66
    POSITIVE LOGITS
    :
    0.50
    ;;
    0.39
    ;
    0.38
     piace
    0.37
    :-
    0.37
     normalt
    0.36
    /*
    0.36
     exhibit
    0.35
     inizi
    0.35
    outSlope
    0.35
    Activations Density 0.025%

    No Known Activations