© 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. 1-CLT-HP
    7. 9267
    Prev
    Next
    INDEX
    Explanations

    member

    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
     gynhyrchwyd
    -0.65
    BeginInit
    -0.60
     protoimpl
    -0.56
     şi
    -0.56
    IUrlHelper
    -0.55
    COLOUR
    -0.55
    UpInside
    -0.54
    Şi
    -0.52
     characterised
    -0.51
    awakeFromNib
    -0.51
    POSITIVE LOGITS
     UserManager
    0.57
     viewType
    0.53
     onBind
    0.52
     урна
    0.52
     Inspector
    0.51
     userDetails
    0.51
     Loon
    0.50
     Arms
    0.50
     Bioaccumulative
    0.49
     specifications
    0.49
    Activations Density 0.012%

    No Known Activations