© 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. 5-CLT-HP
    7. 93460
    Prev
    Next
    INDEX
    Explanations

    Code or generic text

    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
     kasarigan
    -1.26
     المعيارى
    -0.93
    tonsoft
    -0.91
    Personendaten
    -0.90
     تضيفلها
    -0.88
    AnimationsModule
    -0.88
    endphp
    -0.88
    afone
    -0.85
    enderror
    -0.85
    posedge
    -0.81
    POSITIVE LOGITS
     tutto
    0.40
    iene
    0.39
    '
    0.39
    фель
    0.39
     aigu
    0.39
     стро
    0.38
    .
    0.38
    tile
    0.38
    blocking
    0.37
     diret
    0.37
    Activations Density 0.069%

    No Known Activations