© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 15460
    Prev
    Next
    INDEX
    Explanations

    the

    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
    нъ
    -0.57
    hop
    -0.48
    由来
    -0.48
     As
    -0.46
     Thinking
    -0.45
    .
    -0.44
     Using
    -0.44
    ven
    -0.44
    ínű
    -0.43
    loy
    -0.43
    POSITIVE LOGITS
     Jefus
    1.05
     greateſt
    1.02
     Efq
    1.02
     Monfieur
    0.93
    AlterField
    0.91
     myſelf
    0.91
    ſelf
    0.90
     Anſ
    0.90
     Majefty
    0.89
     Theſe
    0.88
    Activations Density 0.027%

    No Known Activations