© 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. 5754
    Prev
    Next
    INDEX
    Explanations

    code and data

    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
    ์
    -0.48
     pungkas
    -0.48
    waitKey
    -0.48
     klaar
    -0.48
    konfirmasi
    -0.47
    rs
    -0.46
    Rourke
    -0.45
    вості
    -0.44
     Wow
    -0.44
     wow
    -0.44
    POSITIVE LOGITS
    IsMutable
    0.61
     للاسماء
    0.57
     MonoBehaviour
    0.57
    KURZBESCHREIBUNG
    0.57
    LabelTagHelper
    0.56
     budgeted
    0.56
    IndentedString
    0.55
     austerity
    0.54
    antMatchers
    0.53
    TRIBUN
    0.52
    Activations Density 0.005%

    No Known Activations