© 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. 5-CLT-HP
    7. 96971
    Prev
    Next
    INDEX
    Explanations

    study

    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
    expandindo
    -0.65
    Hentet
    -0.63
     ddelweddau
    -0.58
     autorytatywna
    -0.57
     &___
    -0.56
    BeginContext
    -0.52
     EnglishChoose
    -0.50
     /\.(
    -0.50
    Архівовано
    -0.50
     أجل
    -0.50
    POSITIVE LOGITS
     and
    0.61
     himſelf
    0.61
     themſelves
    0.58
    nologue
    0.58
    
    0.56
     from
    0.56
     theſe
    0.52
     ſeveral
    0.50
    FirebaseDatabase
    0.49
     whoſe
    0.49
    Activations Density 0.002%

    No Known Activations