© 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. 5-CLT-HP
    7. 91543
    Prev
    Next
    INDEX
    Explanations

    middle

    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
     CreateTagHelper
    -0.69
    enumi
    -0.58
     FontWeight
    -0.56
     CURIAM
    -0.55
     جغرافيا
    -0.53
     StringVar
    -0.53
     oreilles
    -0.50
     становника
    -0.50
    HomeAsUpEnabled
    -0.49
     Così
    -0.48
    POSITIVE LOGITS
    IndentedString
    0.55
     bezeichneter
    0.54
     cheated
    0.51
     roth
    0.48
    Affirmed
    0.48
    vertisers
    0.48
     Administrativna
    0.48
     initComponents
    0.47
    ంది
    0.46
     behaviours
    0.46
    Activations Density 0.002%

    No Known Activations