© 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. 4-CLT-HP
    7. 1000
    Prev
    Next
    INDEX
    Explanations

    to

    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
     nahilalakip
    -0.85
     EconPapers
    -0.59
    ="@+
    -0.56
    roek
    -0.55
    webElement
    -0.51
    jecture
    -0.50
    ExecuteReader
    -0.49
    rscheinlichkeit
    -0.49
     rootReducer
    -0.49
    ειτουργ
    -0.49
    POSITIVE LOGITS
    <bos>
    0.73
     linkovi
    0.64
    RefNanny
    0.59
     saites
    0.59
    tagHelperRunner
    0.52
    ADVERTISEMENT
    0.50
    EndTag
    0.47
     Lerner
    0.47
     AssemblyProduct
    0.46
    TabIndex
    0.46
    Activations Density 0.009%

    No Known Activations