© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40491
    Prev
    Next
    INDEX
    Explanations

    integrity

    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
     StatelessWidget
    -1.23
     signing
    -1.06
     turning
    -0.88
    UnusedPrivate
    -0.88
    IntoConstraints
    -0.88
     Signing
    -0.87
    httphttps
    -0.85
    rungsseite
    -0.85
    Tikang
    -0.84
    OCCURRED
    -0.82
    POSITIVE LOGITS
    まま
    0.45
    vito
    0.45
     List
    0.42
    setdefault
    0.41
     poto
    0.41
    iomanip
    0.40
     up
    0.40
    c
    0.39
     限
    0.39
                                   
    0.39
    Activations Density 0.056%

    No Known Activations