© 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. 10297
    Prev
    Next
    INDEX
    Explanations

    ie/ies

    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
    løs
    -0.65
     plagues
    -0.59
    épendance
    -0.58
    PageModule
    -0.58
    illère
    -0.58
    zeera
    -0.58
     humiliated
    -0.58
     confounded
    -0.57
    polation
    -0.57
    AnchorStyles
    -0.57
    POSITIVE LOGITS
    enumi
    0.55
     StatefulWidget
    0.54
    Autoritní
    0.52
     <<<<<<<<<<<<<<
    0.52
     estekak
    0.45
     Biôgrafia
    0.44
    __":
    0.44
    новниш
    0.43
    <?
    0.43
    Tracce
    0.42
    Activations Density 0.144%

    No Known Activations