© 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. 5-CLT-HP
    7. 96492
    Prev
    Next
    INDEX
    Explanations

    sources of information

    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
    IFIC
    -0.49
    PageIndex
    -0.49
    routeProvider
    -0.47
    úgó
    -0.47
    SupportActionBar
    -0.46
    RegressionTest
    -0.46
    ngrx
    -0.45
    avedra
    -0.45
    initComponents
    -0.44
     '\\;'
    -0.44
    POSITIVE LOGITS
    Hochspringen
    0.63
    Décès
    0.59
     كومونز
    0.58
    itattu
    0.58
     najbol
    0.57
     qualifié
    0.57
     Wicidata
    0.57
    preferred
    0.56
    ngo
    0.55
     rapporti
    0.54
    Activations Density 0.007%

    No Known Activations