© 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. 1-CLT-HP
    7. 8735
    Prev
    Next
    INDEX
    Explanations

    standards

    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
     STANDARDS
    -0.60
     standards
    -0.60
     of
    -0.59
    <bos>
    -0.57
    standards
    -0.56
     Standards
    -0.56
     nakalista
    -0.54
    Standards
    -0.52
    of
    -0.52
    OfDay
    -0.52
    POSITIVE LOGITS
    IsMutable
    0.86
    queryInterface
    0.70
    MemoryWarning
    0.69
    LookAnd
    0.69
    tagHelperRunner
    0.68
    IndentedString
    0.68
    StoryboardSegue
    0.65
    InputTagHelper
    0.65
     sqlSession
    0.65
    IntoConstraints
    0.61
    Activations Density 0.065%

    No Known Activations