© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 6149
    Prev
    Next
    INDEX
    Explanations

    using import

    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
    Negative Logits
    PerformLayout
    -0.82
     '\\;'
    -0.70
    StructEnd
    -0.59
     protoimpl
    -0.57
    LookAnd
    -0.56
     picioare
    -0.55
    Manbalar
    -0.55
    atified
    -0.55
     đương
    -0.55
    lemény
    -0.54
    POSITIVE LOGITS
    enumii
    0.73
    )"),
    0.66
    BeginContext
    0.56
    )");
    0.54
    >");
    0.52
    InteropServices
    0.51
    XmlType
    0.50
    ácara
    0.50
    VITA
    0.50
     <>",
    0.48
    Activations Density 0.007%

    No Known Activations