© 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. 1-CLT-HP
    7. 10523
    Prev
    Next
    INDEX
    Explanations

    bunnies

    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
     linkovi
    -0.57
     OTHERWISE
    -0.55
    DebuggerNonUser
    -0.55
    AnchorTagHelper
    -0.54
    umeric
    -0.53
     Pugh
    -0.53
    sepeda
    -0.52
    DeepCopy
    -0.52
     "..\..\
    -0.51
    ารถ
    -0.51
    POSITIVE LOGITS
    tagHelperRunner
    0.74
    
    0.71
    Tikang
    0.70
    ers
    0.63
    fromnode
    0.60
    expandindo
    0.55
    afficheront
    0.53
    zeera
    0.52
    theoremstyle
    0.51
    BeginContext
    0.50
    Activations Density 0.067%

    No Known Activations