© 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. 10139
    Prev
    Next
    INDEX
    Explanations

    day

    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
    endphp
    -0.75
    AddTagHelper
    -0.73
    uxxxx
    -0.66
    JNIEnv
    -0.66
     CreateTagHelper
    -0.65
    الإنجليزية
    -0.65
    Rhestr
    -0.60
    findpost
    -0.60
     препратки
    -0.58
     StatelessWidget
    -0.58
    POSITIVE LOGITS
    Shine
    0.47
    lat
    0.47
    fo
    0.46
     lac
    0.46
    Lat
    0.46
    anton
    0.45
    lac
    0.45
    styrelsen
    0.43
     Lat
    0.43
    lingen
    0.43
    Activations Density 0.010%

    No Known Activations