© 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. 20-CLT-HP
    7. 78176
    Prev
    Next
    INDEX
    Explanations

    technical documents

    np_max-act-logits · 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
    StructEnd
    -0.74
    ngdoc
    -0.73
     AssemblyTitle
    -0.70
    +#+#
    -0.70
    CodeAttribute
    -0.68
    FormBorderStyle
    -0.63
    sidemargin
    -0.61
    tagHelperRunner
    -0.60
    TagHelper
    -0.60
    EditorBrowsable
    -0.58
    POSITIVE LOGITS
    ix
    0.55
    ixx
    0.52
     Segurança
    0.47
    ikh
    0.44
    ye
    0.44
     JOUR
    0.43
    Ij
    0.43
     geodes
    0.43
    je
    0.43
     journals
    0.42
    Activations Density 0.000%

    No Known Activations