© 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. 5-CLT-HP
    7. 4980
    Prev
    Next
    INDEX
    Explanations

    Russian/Programming Code

    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
    GOTREF
    -0.49
    setVerticalGroup
    -0.47
     المعيارى
    -0.47
    subpackage
    -0.46
    قب
    -0.45
    extAlignment
    -0.44
    Ligações
    -0.44
    FieldOffset
    -0.44
     loc
    -0.42
    ijų
    -0.42
    POSITIVE LOGITS
    AMENT
    0.57
    tagHelperRunner
    0.56
    ament
    0.52
     propOrder
    0.52
    ostante
    0.51
    jsonwebtoken
    0.49
    RunAsync
    0.49
    étricas
    0.48
    CloseOperation
    0.48
    PreferredItem
    0.48
    Activations Density 0.002%

    No Known Activations