© 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. 9557
    Prev
    Next
    INDEX
    Explanations

    schoolchildren and commercials

    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
     comigo
    -0.58
    utilisons
    -0.53
     تضيفلها
    -0.52
     LEYENDO
    -0.52
    momix
    -0.51
     magasiner
    -0.51
     Drury
    -0.50
     redonde
    -0.50
    verwijspagina
    -0.50
     vayas
    -0.50
    POSITIVE LOGITS
    Traits
    0.58
    EndInit
    0.57
    principalTable
    0.56
     onCreateView
    0.52
     hoạch
    0.52
     visited
    0.51
    ChildScrollView
    0.51
     naselje
    0.50
    juste
    0.50
    FormsModule
    0.50
    Activations Density 0.007%

    No Known Activations