© 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. 5-CLT-HP
    7. 91202
    Prev
    Next
    INDEX
    Explanations

    ';

    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
    Cyfeiriadau
    -0.75
    oneofs
    -0.74
    GraphicsUnit
    -0.72
    __':
    -0.71
    __":
    -0.69
    
    -0.68
    Personendaten
    -0.68
     noDo
    -0.67
     pinulongan
    -0.67
    AddTagHelper
    -0.66
    POSITIVE LOGITS
     yeah
    0.55
     fast
    0.52
    ,
    0.52
     here
    0.50
     Fast
    0.49
    .
    0.49
     what
    0.49
     voici
    0.47
     how
    0.44
     profiles
    0.42
    Activations Density 0.000%

    No Known Activations