© 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. 0-CLT-HP
    7. 95661
    Prev
    Next
    INDEX
    Explanations

    News/Legal/Official documents

    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
     fernández
    -0.55
     pleaſure
    -0.52
     ſur
    -0.51
     ſta
    -0.51
     ſol
    -0.50
     ſay
    -0.50
     ſon
    -0.49
     ſte
    -0.48
     himſelf
    -0.47
     ſen
    -0.45
    POSITIVE LOGITS
    AndEndTag
    1.00
     виправивши
    0.84
    +#+#
    0.81
    DoubleQuotes
    0.78
    ]")]
    0.76
    AddTagHelper
    0.75
     GenerationType
    0.74
    uxxxx
    0.74
     nahilalakip
    0.72
     <=",
    0.71
    Activations Density 0.198%

    No Known Activations