© 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. 5-CLT-HP
    7. 3555
    Prev
    Next
    INDEX
    Explanations

    creation/construction

    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
     produced
    -0.48
     created
    -0.46
     a
    -0.46
     out
    -0.44
    BUL
    -0.43
    vieto
    -0.43
    built
    -0.42
    Miejs
    -0.40
    製作
    -0.40
     up
    -0.40
    POSITIVE LOGITS
     resourceCulture
    0.87
     GetEnumerator
    0.74
     للاسماء
    0.73
     للمعارف
    0.70
    хьтан
    0.67
     ddelweddau
    0.67
    rawDesc
    0.67
    parsedMessage
    0.66
    stdc
    0.66
    InitVars
    0.66
    Activations Density 0.001%

    No Known Activations