© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12975
    Prev
    Next
    INDEX
    Explanations

    lifetime

    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
     تضيفلها
    -0.63
     propOrder
    -0.54
    曖昧さ回避
    -0.52
    ButterKnife
    -0.52
    出版年
    -0.51
    UnusedPrivate
    -0.51
     שוליים
    -0.50
    mici
    -0.50
     DbType
    -0.50
    nahme
    -0.50
    POSITIVE LOGITS
    routeProvider
    0.75
    __(/*!
    0.59
     MainAxisSize
    0.54
     RemoteException
    0.54
    RunAsync
    0.53
     Sall
    0.50
    #+#
    0.47
    ("$.
    0.46
    getDoctrine
    0.46
     Hered
    0.46
    Activations Density 0.004%

    No Known Activations