© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 158
    Prev
    Next
    INDEX
    Explanations

    technical documentation and stories

    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
     mie
    -0.49
    ets
    -0.48
    Visual
    -0.47
     exerted
    -0.47
     Straus
    -0.47
    thora
    -0.47
     Haush
    -0.47
    LEncoder
    -0.46
    ors
    -0.45
    istic
    -0.45
    POSITIVE LOGITS
     resourceCulture
    0.79
    Personendaten
    0.71
     protoimpl
    0.71
     transfieras
    0.70
    blockList
    0.67
    LabelTagHelper
    0.63
    
    0.63
     محفوظة
    0.60
    djangoproject
    0.60
    expandindo
    0.60
    Activations Density 0.019%

    No Known Activations