© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41184
    Prev
    Next
    INDEX
    Explanations

    creatic

    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
    creatic
    -1.57
    creas
    -0.82
    Pretty
    -0.52
    standig
    -0.48
    glBind
    -0.48
     multiplicative
    -0.48
    openqa
    -0.47
    MultipartFile
    -0.45
    cplusplus
    -0.44
    matchCondition
    -0.44
    POSITIVE LOGITS
     aDecoder
    0.71
    soever
    0.68
     Potomac
    0.61
    TagHelper
    0.60
     vulgares
    0.58
     IMDG
    0.57
     Duk
    0.57
     betweenstory
    0.57
    trib
    0.56
    essentiel
    0.56
    Activations Density 0.580%

    No Known Activations