© 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. 20-CLT-HP
    7. 73627
    Prev
    Next
    INDEX
    Explanations

    Code and science snippets

    np_max-act-logits · 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
     AssemblyCulture
    -0.78
    المناصب
    -0.62
    UrlResolution
    -0.61
    nieren
    -0.59
    StoryboardSegue
    -0.59
     MCI
    -0.58
    EndInit
    -0.56
     YG
    -0.56
     Makassar
    -0.56
     circulated
    -0.55
    POSITIVE LOGITS
     MainAxisSize
    0.59
    ativement
    0.48
    KommentareTeilen
    0.45
     AspNetCore
    0.44
     Comfor
    0.43
    ESTAMP
    0.42
    ANTLR
    0.40
    hspace
    0.40
    身为
    0.40
    BagConstraints
    0.40
    Activations Density 0.000%

    No Known Activations