© 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. 0-CLT-HP
    7. 38615
    Prev
    Next
    INDEX
    Explanations

    roads, excuses, evangelism

    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
    IsContent
    -0.80
     protoimpl
    -0.54
    )");
    -0.54
     Blvd
    -0.53
     AssemblyTitle
    -0.53
    urahan
    -0.53
     excuse
    -0.52
     Molo
    -0.52
    __).
    -0.52
     spreading
    -0.51
    POSITIVE LOGITS
     precisione
    0.69
     démo
    0.64
     selezione
    0.64
     inconvénients
    0.63
     rêves
    0.62
     oreilles
    0.62
     eccell
    0.61
     peuples
    0.61
     chaude
    0.60
     varandra
    0.60
    Activations Density 0.546%

    No Known Activations