© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 16235
    Prev
    Next
    INDEX
    Explanations

    routes or methods

    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
    Negative Logits
    DebuggerNonUser
    -0.50
    ///</
    -0.50
    RegisterType
    -0.48
    さまで
    -0.45
    rawDesc
    -0.44
    yntaxException
    -0.44
    trab
    -0.43
    adeira
    -0.42
    WireFormatLite
    -0.42
    ENSA
    -0.42
    POSITIVE LOGITS
     houſe
    0.72
    setVerticalGroup
    0.70
     themſelves
    0.70
     Monfieur
    0.69
     myſelf
    0.68
     ſtate
    0.66
     leaſt
    0.66
     Eſ
    0.66
     Efq
    0.65
     fubject
    0.65
    Activations Density 0.019%

    No Known Activations