© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40076
    Prev
    Next
    INDEX
    Explanations

    Central

    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
     Central
    -0.48
    i
    -0.47
     Miss
    -0.42
    шко
    -0.41
     non
    -0.40
     
    -0.40
    iv
    -0.40
    af
    -0.39
     k
    -0.39
    Central
    -0.39
    POSITIVE LOGITS
     Мексичка
    1.26
    AnchorStyles
    1.19
     مرئيه
    1.17
     AssemblyTitle
    1.09
     MainAxisSize
    1.09
     MessageBoxIcon
    1.04
    +#+
    1.02
    MethodManager
    1.02
     utafitiHapana
    1.02
     iconFacebook
    1.02
    Activations Density 0.482%

    No Known Activations