© 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. 3387
    Prev
    Next
    INDEX
    Explanations

    USCIS

    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
    principalColumn
    -0.66
    Diwedd
    -0.55
     intptr
    -0.50
     Zacks
    -0.47
    }^{-}\
    -0.47
    reactivex
    -0.47
     linkovi
    -0.47
    Jeografia
    -0.46
    glGen
    -0.46
    __)
    -0.46
    POSITIVE LOGITS
     Monfieur
    0.66
     pleaſure
    0.66
    Gemeinden
    0.65
    Filmografia
    0.61
     trajets
    0.60
     Efq
    0.60
     Conſ
    0.59
    脚注の使い方
    0.59
     July
    0.56
     unſ
    0.56
    Activations Density 0.010%

    No Known Activations