© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1267
    Prev
    Next
    INDEX
    Explanations

    9

    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
    VersionUID
    -0.59
     magasiner
    -0.59
    year
    -0.57
     year
    -0.57
     Years
    -0.57
     Year
    -0.56
     YEARS
    -0.56
     YEAR
    -0.55
    Years
    -0.55
    Year
    -0.55
    POSITIVE LOGITS
    Whilst
    0.54
    Enllaces
    0.52
     grade
    0.52
    =>'
    0.50
     programme
    0.49
    textTheme
    0.49
    isbury
    0.48
     prawn
    0.47
     Hors
    0.47
    Honours
    0.47
    Activations Density 0.001%

    No Known Activations