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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 1020
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
     
    -0.49
    uket
    -0.39
     Max
    -0.38
     in
    -0.37
     AssemblyCompany
    -0.37
    aru
    -0.37
     BoxDecoration
    -0.36
     N
    -0.36
    гән
    -0.36
     echar
    -0.36
    POSITIVE LOGITS
     Monfieur
    0.91
     ſeveral
    0.90
     purpoſe
    0.88
    ItemBackground
    0.84
    VersionUID
    0.82
     itſelf
    0.82
     Efq
    0.81
     myſelf
    0.81
     ſmall
    0.80
     pleaſure
    0.80
    Activations Density 0.094%

    No Known Activations