© 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. 15538
    Prev
    Next
    INDEX
    Explanations

    Johannesburg

    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
    InjectMocks
    -0.67
    NewUrlParser
    -0.64
    expandindo
    -0.59
    RenderAtEndOf
    -0.57
    ACITY
    -0.56
    MockBean
    -0.55
     motility
    -0.54
    YECTO
    -0.54
     Rizzo
    -0.54
     dàng
    -0.54
    POSITIVE LOGITS
     lèvres
    0.56
     âmes
    0.50
     morire
    0.50
     puissent
    0.50
     soste
    0.48
     états
    0.48
     découvertes
    0.46
     AspNetCore
    0.46
     écrans
    0.45
     linkovi
    0.44
    Activations Density 0.030%

    No Known Activations